© 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. 3-RES-JB
    11. 7816
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting symbols

    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
     corrid
    -0.62
    ãĤ´
    -0.61
     lifes
    -0.58
    ¶ħ
    -0.53
     garner
    -0.52
     compr
    -0.52
    ãĤ´ãĥ³
    -0.52
     asylum
    -0.51
    ãĤ°
    -0.51
     Heist
    -0.51
    POSITIVE LOGITS
    fy
    0.80
    ean
    0.69
    yss
    0.68
    meric
    0.64
    erb
    0.63
     annexed
    0.62
     uh
    0.60
    Pg
    0.60
    zech
    0.59
    ht
    0.59
    Activations Density 1.291%

    No Known Activations