© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6741
    Prev
    Next
    INDEX
    Explanations

    phrases related to titles or names with quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly quotation marks

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

    No Comments

    Negative Logits
    ²¾
    -0.83
    ¬¼
    -0.79
    cha
    -0.74
    senal
    -0.72
    ĻĤ
    -0.70
     favourites
    -0.66
    comings
    -0.66
    acas
    -0.63
    ife
    -0.63
    thur
    -0.62
    POSITIVE LOGITS
    /"
    0.87
     implying
    0.83
     referring
    0.81
    SPONSORED
    0.79
     aka
    0.78
    agy
    0.75
     meaning
    0.75
     according
    0.74
    >>\
    0.72
     namely
    0.71
    Activations Density 0.073%

    No Known Activations