© 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. 10-RES-JB
    11. 10011
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or direction

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical and numerical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roups
    -0.93
    zens
    -0.86
    illions
    -0.83
    undreds
    -0.78
    nces
    -0.76
    enaries
    -0.74
    itures
    -0.73
    endars
    -0.73
    azines
    -0.70
    ousands
    -0.69
    POSITIVE LOGITS
     antagonist
    0.74
     adversary
    0.70
     abuser
    0.69
     dreaded
    0.69
     torment
    0.67
     dilemma
    0.67
     susceptibility
    0.66
     intruder
    0.66
     perpetrator
    0.65
     traitor
    0.64
    Activations Density 0.999%

    No Known Activations