© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Mull" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mull" and its variations in context

    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
     Scient
    -0.69
     Skydragon
    -0.68
     Coral
    -0.63
    IRO
    -0.60
    ãģ®æ
    -0.60
     HERO
    -0.58
    VALUE
    -0.58
     Destiny
    -0.57
     OECD
    -0.57
     Amend
    -0.57
    POSITIVE LOGITS
    igan
    1.25
    igans
    1.13
    ahs
    1.08
    iard
    0.92
    okin
    0.92
    atto
    0.91
    essee
    0.91
    ipop
    0.90
    iewicz
    0.90
    oway
    0.89
    Activations Density 0.053%

    No Known Activations