© 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. 40340
    Prev
    Next
    INDEX
    Explanations

    mentions of LGBTQ+ Pride events and related topics

    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
    578
    +0.13
    0.7%
    496
    +0.12
    0.7%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.21
    326
    +0.12
    0.18
    709
    +0.09
    0.09
    Negative Logits
    opathy
    -0.71
    oxide
    -0.70
    iago
    -0.68
    oxin
    -0.65
    odic
    -0.64
    pered
    -0.63
    obe
    -0.62
    onte
    -0.60
    cephal
    -0.58
    iology
    -0.58
    POSITIVE LOGITS
     Agenda
    0.63
     Riders
    0.59
    glers
    0.59
     nightclub
    0.57
     Pride
    0.57
    edIn
    0.57
    Berry
    0.56
     ambassadors
    0.55
     Byrne
    0.53
    rers
    0.52
    Activations Density 5.532%

    No Known Activations