© 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. 3-RES-JB
    11. 10719
    Prev
    Next
    INDEX
    Explanations

    various types of categories or classifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating variety or multiple categories of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.81
    LAN
    -0.74
    edia
    -0.71
    adium
    -0.70
    Recomm
    -0.68
    hani
    -0.67
    Interstitial
    -0.66
    mented
    -0.66
    mary
    -0.66
    aeper
    -0.66
    POSITIVE LOGITS
    etter
    0.92
    hots
    0.81
    chool
    0.79
    paces
    0.77
    pace
    0.76
    etting
    0.76
    afe
    0.73
    ucker
    0.70
    cue
    0.66
    ãĥĺ
    0.66
    Activations Density 0.016%

    No Known Activations