© 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. 7-RES-JB
    11. 13460
    Prev
    Next
    INDEX
    Explanations

    adjectives related to size, strength, and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sense of measurement or assessment related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.73
    igma
    -0.63
    efully
    -0.63
    ghai
    -0.63
    igmatic
    -0.63
    Baltimore
    -0.62
    ucket
    -0.62
    inois
    -0.62
    ertodd
    -0.61
    acci
    -0.61
    POSITIVE LOGITS
     course
    0.82
     sorts
    0.77
    course
    0.62
    tnc
    0.60
    ELD
    0.60
    uggets
    0.58
     doubtful
    0.58
     Ends
    0.58
     materials
    0.58
     dubious
    0.57
    Activations Density 0.241%

    No Known Activations