Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45805
    Prev
    Next
    INDEX
    Explanations

    phrases related to informing or the dissemination of various types of information

    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
    679
    +0.12
    0.7%
    447
    +0.10
    0.6%
    336
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.12
    0.03
    108
    +0.10
    0.05
    336
    +0.08
    0.03
    Negative Logits
    ingu
    -0.57
    enf
    -0.51
    Kings
    -0.50
     Kings
    -0.48
    imposed
    -0.48
    Pain
    -0.47
    KING
    -0.46
    cessive
    -0.45
    dog
    -0.45
     vain
    -0.44
    POSITIVE LOGITS
    ally
    0.89
    omic
    0.72
     inform
    0.66
    acies
    0.64
    tale
    0.61
    ality
    0.60
    ingly
    0.58
    atics
    0.57
    aci
    0.57
    urally
    0.55
    Activations Density 6.749%

    No Known Activations