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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 58
    Prev
    Next
    INDEX
    Explanations

    It appears that Neuron 4 does not show any activation for the given inputs, suggesting that it is not finding the specific feature or pattern it is designed to detect within this text. Therefore, there is no activation or feature identified by Neuron 4 in the provided samples

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqor
    -0.80
     seams
    -0.71
     eyed
    -0.68
    oshenko
    -0.65
     glim
    -0.64
     untrue
    -0.63
     demos
    -0.63
     shader
    -0.63
     Witches
    -0.62
     pse
    -0.62
    POSITIVE LOGITS
    ¥µ
    0.66
    rive
    0.66
    utm
    0.64
    iday
    0.63
    ér
    0.62
    rug
    0.61
    spection
    0.61
     CrossRef
    0.60
    ij士
    0.60
    athing
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.