© 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. 3-RES-JB
    11. 21223
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific objects or entities, particularly related to names or nouns

    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
    ccording
    -0.66
     GOODMAN
    -0.65
     tremend
    -0.61
    staking
    -0.58
    PDATE
    -0.58
     reluct
    -0.57
     denomin
    -0.57
    âĸ¬
    -0.55
     corrid
    -0.55
     subscript
    -0.55
    POSITIVE LOGITS
    ensis
    0.91
    aten
    0.70
    ati
    0.69
     III
    0.66
    aii
    0.66
     ("
    0.66
     ('
    0.66
    istan
    0.65
    hene
    0.65
    iev
    0.64
    Activations Density 0.951%

    No Known Activations