© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    strong emotional and impactful phrases or sentences

    oai_token-act-pair · gpt-3.5-turbo

    the symbol 'âĢ', which appears consistently across various contexts in the document

    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
     decomp
    -0.74
     scatter
    -0.72
     monop
    -0.71
     cyan
    -0.68
     cottage
    -0.67
     shack
    -0.66
     corrections
    -0.64
     forwarded
    -0.64
     charm
    -0.63
     radar
    -0.63
    POSITIVE LOGITS
    £
    0.89
    Hon
    0.79
    catentry
    0.78
    º
    0.77
    ISIS
    0.74
    âĢķ
    0.74
    ¹
    0.74
    ¢
    0.74
    Serv
    0.72
    Vo
    0.72
    Activations Density 0.550%

    No Known Activations