Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17587
    Prev
    Next
    INDEX
    Explanations

    pronouns and body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to physical actions involving grabbing or holding

    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
    appa
    -0.80
    arth
    -0.74
    jury
    -0.68
    arcity
    -0.67
    onna
    -0.63
    eller
    -0.62
    clusive
    -0.62
    arning
    -0.62
    idia
    -0.61
    istor
    -0.61
    POSITIVE LOGITS
    ById
    1.08
     reins
    0.85
    hold
    0.83
     foothold
    0.78
     keys
    0.76
     bearings
    0.74
     opp
    0.73
     coveted
    0.70
     attention
    0.69
     opportunity
    0.69
    Activations Density 0.247%

    No Known Activations