© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 12837
    Prev
    Next
    INDEX
    Explanations

    words related to clothing or professions, particularly with a focus on hairdressing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bird" and its variations

    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
    ptive
    -0.78
    perature
    -0.75
    ptives
    -0.67
    uble
    -0.66
    ILA
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
     hemor
    -0.64
    æł
    -0.64
    course
    -0.64
    prus
    -0.64
    POSITIVE LOGITS
    seed
    0.84
    orf
    0.84
    odge
    0.78
    ing
    0.78
    ricks
    0.77
    ird
    0.77
    ressing
    0.77
    ness
    0.77
    ress
    0.76
    ed
    0.75
    Activations Density 0.022%

    No Known Activations