© 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. 11-RES-JB
    11. 24093
    Prev
    Next
    INDEX
    Explanations

    phrases related to making definitive statements and decisions

    oai_token-act-pair · gpt-3.5-turbo

    reference to personal authority or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thouse
    -0.63
    liest
    -0.59
    linger
    -0.52
     tong
    -0.52
    hma
    -0.52
    lington
    -0.51
    laus
    -0.50
    /-
    -0.48
    des
    -0.48
     ourselves
    -0.48
    POSITIVE LOGITS
     Territories
    0.58
    ATIONS
    0.57
    aution
    0.55
    ATED
    0.53
    ATIVE
    0.53
    adow
    0.51
    AD
    0.51
    andi
    0.51
    allowed
    0.50
    occup
    0.50
    Activations Density 0.328%

    No Known Activations