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. 10-RES-JB
    6. 3518
    Prev
    Next
    INDEX
    Explanations

    references to 'human' or human-related characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being human

    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
    href
    -0.75
    soDeliveryDate
    -0.74
    é¾įå
    -0.68
    RET
    -0.67
    argon
    -0.64
    urations
    -0.63
    UGE
    -0.63
     Comprehensive
    -0.62
    EMP
    -0.62
    CCC
    -0.62
    POSITIVE LOGITS
     beings
    1.44
    oids
    1.18
    itarian
    1.14
    itar
    1.12
    oid
    1.12
    istic
    1.06
    izing
    1.03
    ized
    1.01
     readable
    0.98
    istically
    0.94
    Activations Density 0.029%

    No Known Activations