© 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. 2-RES-JB
    11. 9411
    Prev
    Next
    INDEX
    Explanations

    keywords related to permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "allow" in various contexts related to permissions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soldier
    -0.75
     Scream
    -0.70
    tch
    -0.65
    kaya
    -0.63
    kun
    -0.63
     Roc
    -0.60
    kind
    -0.59
    Sac
    -0.58
    lla
    -0.58
    star
    -0.58
    POSITIVE LOGITS
    Reviewer
    1.01
    ĸļ
    0.79
    geries
    0.78
    ibaba
    0.76
    Console
    0.75
     permitting
    0.73
    auga
    0.72
    elist
    0.71
    Allows
    0.69
    ances
    0.67
    Activations Density 0.041%

    No Known Activations