© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33084
    Prev
    Next
    INDEX
    Explanations

    phrases referring to political figures and policies in a critical or oppositional context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.13
    0.8%
    430
    +0.08
    0.5%
    642
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.13
    0.21
    739
    +0.08
    0.06
    60
    +0.07
    0.09
    Negative Logits
     chemistry
    -0.47
     retiring
    -0.47
     hesitation
    -0.46
    lander
    -0.46
     congrat
    -0.46
     sanitation
    -0.44
    zik
    -0.42
     condolences
    -0.42
     complication
    -0.42
     Fine
    -0.42
    POSITIVE LOGITS
    soever
    0.85
     mattered
    0.64
     happens
    0.63
    itionally
    0.59
     kinds
    0.58
     carbohyd
    0.55
    ppers
    0.55
    xual
    0.54
    ciating
    0.54
     sorts
    0.53
    Activations Density 6.235%

    No Known Activations