© 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. 0-RES-JB
    11. 23196
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    words related to movie or performance contexts, specifically focusing on actors and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     greens
    -0.66
     Ye
    -0.65
     Ãľ
    -0.64
    ãĥ´
    -0.61
     upl
    -0.59
     Ess
    -0.59
     adaptations
    -0.59
     silhou
    -0.56
     NG
    -0.56
     Rih
    -0.56
    POSITIVE LOGITS
    ctor
    5.20
    ctors
    3.37
    ct
    1.40
    ctory
    1.36
    ector
    1.35
    ctions
    1.25
    zza
    1.22
    ctive
    1.20
    ction
    1.16
    culus
    1.15
    Activations Density 0.020%

    No Known Activations