© 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. 10-RES-JB
    11. 20455
    Prev
    Next
    INDEX
    Explanations

    text related to newsletters or emails

    oai_token-act-pair · gpt-3.5-turbo

    references to an editorial or newsletter format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erman
    -0.67
    atari
    -0.62
    arians
    -0.61
    nar
    -0.58
    ilver
    -0.57
    rian
    -0.56
    arth
    -0.56
    obar
    -0.55
    elo
    -0.55
    arian
    -0.54
    POSITIVE LOGITS
    Ç
    0.55
     chance
    0.54
    âĶĢâĶĢ
    0.53
     versa
    0.53
    ̶
    0.52
     pow
    0.52
     proofs
    0.52
     Picks
    0.52
    â
    0.51
    Tes
    0.51
    Activations Density 0.058%

    No Known Activations