© 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. 7-RES-JB
    11. 24542
    Prev
    Next
    INDEX
    Explanations

    names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incarn
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.73
    venge
    -0.65
     Thief
    -0.64
    Bound
    -0.64
     ILCS
    -0.64
    ãĤ¤ãĥĪ
    -0.64
    eed
    -0.63
     Underworld
    -0.63
    ãĥIJ
    -0.62
    POSITIVE LOGITS
     concedes
    1.04
     admits
    1.01
     concludes
    1.00
     explained
    1.00
     believes
    0.99
     advises
    0.96
     cautioned
    0.95
     conceded
    0.95
     speculate
    0.95
     stressed
    0.94
    Activations Density 0.306%

    No Known Activations