© 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. 11-RES-JB
    11. 4207
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prohibition or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teasp
    -0.71
     exting
    -0.69
    nai
    -0.68
    eele
    -0.68
    ftime
    -0.67
    maxwell
    -0.66
    ©¶æ¥µ
    -0.66
    mone
    -0.65
    Interstitial
    -0.63
    aturdays
    -0.62
    POSITIVE LOGITS
     them
    1.64
     us
    1.37
     THEM
    1.19
     him
    1.16
    them
    1.11
     theirs
    1.04
     themselves
    0.99
     me
    0.96
     Them
    0.95
     itself
    0.92
    Activations Density 0.450%

    No Known Activations