© 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. 15199
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms or phrases enclosed in single quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that are enclosed in 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
    Ļ½
    -0.91
    ĻĤ
    -0.84
    ¸
    -0.75
    ighed
    -0.74
    ilst
    -0.71
    forcement
    -0.70
    shr
    -0.69
    İĭ
    -0.69
    ãĥ¼ãĥ«
    -0.68
    umat
    -0.68
    POSITIVE LOGITS
     motto
    0.70
     moniker
    0.67
    SPONSORED
    0.66
    /"
    0.64
     ;)
    0.63
    hood
    0.60
    ',
    0.59
     fixation
    0.58
     fortun
    0.58
    -'
    0.58
    Activations Density 0.042%

    No Known Activations