Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 287
    Prev
    Next
    INDEX
    Explanations

    legal or official actions, especially those involving prohibitions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "barred" and related entities or individuals

    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
    oke
    -0.72
     ECO
    -0.72
     Sek
    -0.69
    NP
    -0.68
    CC
    -0.67
    PP
    -0.67
     Dani
    -0.66
    Occ
    -0.65
    CCC
    -0.63
     Comp
    -0.63
    POSITIVE LOGITS
     barred
    2.49
    fred
    1.50
    smith
    1.20
     ginger
    1.12
     hanged
    1.01
    umbered
    0.94
     Spiegel
    0.92
     hinges
    0.90
     Lobby
    0.89
     hob
    0.85
    Activations Density 0.029%

    No Known Activations