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. 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. 1959
    Prev
    Next
    INDEX
    Explanations

    software and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses or other punctuation marks

    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
     answ
    -0.72
    ciating
    -0.70
    omore
    -0.66
    itory
    -0.66
    igmatic
    -0.57
    rew
    -0.55
    ignt
    -0.55
    front
    -0.54
    etta
    -0.53
     administrator
    -0.53
    POSITIVE LOGITS
     Frames
    0.63
     Committees
    0.63
    âķ
    0.58
    76561
    0.57
    RESULTS
    0.56
    )))
    0.54
    *)
    0.54
    ãĥİ
    0.54
    Reply
    0.54
     IMAGES
    0.54
    Activations Density 0.157%

    No Known Activations