© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    words related to physical attachment or connection

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hook" and its variations

    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
     Scotia
    -0.81
    ————
    -0.70
    zza
    -0.69
    rees
    -0.67
     Nieto
    -0.64
    cles
    -0.61
    ndum
    -0.58
    ãĥ´
    -0.58
     enrichment
    -0.57
    âĸº
    -0.57
    POSITIVE LOGITS
    tail
    1.10
    tails
    1.07
    worms
    1.06
    worm
    1.05
    ahs
    1.01
    shot
    1.00
    ups
    0.98
    up
    0.96
    hook
    0.92
    masters
    0.92
    Activations Density 0.053%

    No Known Activations