© 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. 8-RES-JB
    11. 20153
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to detailed presentations or explanations

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pigs
    -0.61
     Kills
    -0.56
     kills
    -0.52
    ittens
    -0.50
    hate
    -0.50
    indal
    -0.50
     hates
    -0.48
    KO
    -0.48
     kill
    -0.47
    shit
    -0.47
    POSITIVE LOGITS
     nonetheless
    0.75
     nevertheless
    0.73
     wondering
    0.69
     cautiously
    0.67
    pmwiki
    0.65
    ãĤ¦ãĤ¹
    0.65
     understandably
    0.63
    etheless
    0.63
     hopeful
    0.60
     parting
    0.59
    Activations Density 0.850%

    No Known Activations