© 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. 10994
    Prev
    Next
    INDEX
    Explanations

    phrases related to items stored in pockets

    oai_token-act-pair · gpt-3.5-turbo

    references to pockets and items associated with them

    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
     ANGEL
    -0.85
    mberg
    -0.68
    Reviewer
    -0.66
    abad
    -0.65
    ERO
    -0.64
    actionDate
    -0.64
     Relations
    -0.63
    IAS
    -0.61
    jad
    -0.61
    DEF
    -0.60
    POSITIVE LOGITS
    knife
    1.26
    book
    0.93
    notes
    0.93
    books
    0.86
    watch
    0.84
    tex
    0.83
    roll
    0.80
     knife
    0.79
    pocket
    0.77
    bag
    0.76
    Activations Density 0.038%

    No Known Activations