© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20365
    Prev
    Next
    INDEX
    Explanations

    adjectives like "indescribable," "incurable," and "insurmountable."

    oai_token-act-pair · gpt-3.5-turbo

    words that describe various forms of capability or limitation, particularly those emphasizing impossibility or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erva
    -0.93
    hetically
    -0.88
    icion
    -0.87
    alyst
    -0.75
    ickr
    -0.75
    avers
    -0.75
    aeper
    -0.73
    umbn
    -0.73
    iversary
    -0.73
    appropriately
    -0.72
    POSITIVE LOGITS
     Haram
    0.84
     Islands
    0.74
     proportions
    0.72
     Skies
    0.72
     unlaw
    0.70
     Danger
    0.68
     volumes
    0.68
     mysteries
    0.67
    adoes
    0.66
     coil
    0.65
    Activations Density 0.058%

    No Known Activations