© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    references to TV networks or stations

    oai_token-act-pair · gpt-3.5-turbo

    references to television networks or channels

    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
    leans
    -0.80
    hammad
    -0.79
    hot
    -0.71
    20439
    -0.69
    hend
    -0.67
    uten
    -0.67
    currency
    -0.67
    places
    -0.66
    ename
    -0.66
    pell
    -0.65
    POSITIVE LOGITS
    ILLE
    1.43
    NZ
    1.02
     Everywhere
    0.91
     Channel
    0.83
    Sav
    0.83
    ideo
    0.82
    ODUCT
    0.79
    trop
    0.79
    OS
    0.75
     Broadcasting
    0.73
    Activations Density 0.023%

    No Known Activations