© 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. 8-RES-JB
    11. 6151
    Prev
    Next
    INDEX
    Explanations

    terms related to physical objects or products

    oai_token-act-pair · gpt-3.5-turbo

    references to physical items or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.83
    uits
    -0.82
    ucker
    -0.80
    emi
    -0.80
    oleon
    -0.79
    appropriately
    -0.79
    acus
    -0.79
    wana
    -0.77
    chief
    -0.77
    oi
    -0.76
    POSITIVE LOGITS
     versions
    1.24
     copies
    1.08
     version
    1.05
     equivalents
    1.02
     copy
    1.02
     counterparts
    0.97
     counterpart
    0.88
    izable
    0.87
     alternatives
    0.86
     equivalent
    0.84
    Activations Density 0.330%

    No Known Activations