© 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. 6-RES-JB
    11. 646
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coli
    -0.79
     seiz
    -0.56
     reven
    -0.56
     airspace
    -0.54
     citiz
    -0.53
    Ĭ±
    -0.51
    pard
    -0.50
     avenues
    -0.50
     comprehens
    -0.50
    Condition
    -0.49
    POSITIVE LOGITS
    reau
    0.83
     Trog
    0.62
    utra
    0.60
    zinski
    0.57
     Brothers
    0.57
    Bone
    0.53
    oola
    0.53
     pedals
    0.53
    ongyang
    0.52
    sels
    0.51
    Activations Density 1.229%

    No Known Activations