© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2894
    Prev
    Next
    INDEX
    Explanations

    numerical rankings or positions such as first, second, third, etc., in competitive contexts

    oai_token-act-pair · gpt-3.5-turbo

    rankings or positions in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.88
    natureconservancy
    -0.77
    asted
    -0.69
    afer
    -0.68
    aceous
    -0.68
    CHAT
    -0.67
    yll
    -0.65
     Warn
    -0.64
     Rudd
    -0.63
     Travels
    -0.63
    POSITIVE LOGITS
    upon
    0.80
    holders
    0.78
    holder
    0.78
    ername
    0.78
    manship
    0.69
    cmp
    0.68
    ieve
    0.67
    bos
    0.66
    stick
    0.66
     digits
    0.66
    Activations Density 0.027%

    No Known Activations