© 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. 8494
    Prev
    Next
    INDEX
    Explanations

    phrases related to confrontations or direct interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    references to facial interactions or displays

    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
    roups
    -0.78
    ocket
    -0.76
    estones
    -0.73
    sites
    -0.70
    erest
    -0.70
    atform
    -0.68
     Fancy
    -0.67
    iston
    -0.67
    akings
    -0.67
    imore
    -0.66
    POSITIVE LOGITS
    pal
    0.73
     adversity
    0.72
    ciating
    0.71
    utor
    0.70
     Predator
    0.70
    ãĥ¼ãĥ
    0.69
    NYSE
    0.65
     condesc
    0.64
     backdrop
    0.63
     discrimination
    0.62
    Activations Density 0.072%

    No Known Activations