© 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. 18638
    Prev
    Next
    INDEX
    Explanations

    the word "all" followed by a number indicating a high level of quantity or completeness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "all."

    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
     Freeze
    -0.60
     droid
    -0.59
    romeda
    -0.58
     sleeper
    -0.56
     Caption
    -0.56
     Scientist
    -0.55
     Respons
    -0.54
     IPM
    -0.54
     Exile
    -0.54
     Daughter
    -0.53
    POSITIVE LOGITS
    ayed
    1.09
    too
    1.08
     sorts
    1.07
    aying
    1.07
    ocative
    1.06
    udes
    1.03
    oys
    1.01
    edged
    1.01
    ots
    1.00
    ocating
    0.99
    Activations Density 0.101%

    No Known Activations