© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10731
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'cc' followed by a number, potentially indicating a section or category

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token "cc"

    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
     Lans
    -0.82
    velt
    -0.78
    chest
    -0.76
    senal
    -0.73
    ¥µ
    -0.70
    wered
    -0.67
    cknow
    -0.67
    strument
    -0.65
    haul
    -0.64
    esthetic
    -0.63
    POSITIVE LOGITS
    entric
    1.12
    aneers
    1.06
    arthy
    1.05
    inelli
    1.02
    inct
    0.95
    lesi
    0.89
    uzz
    0.89
    artney
    0.89
    ombat
    0.85
    rypt
    0.85
    Activations Density 0.016%

    No Known Activations