© 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. 7-RES-JB
    11. 17212
    Prev
    Next
    INDEX
    Explanations

    phrases indicating new information or reports

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oses
    -0.81
    andem
    -0.80
    ocaust
    -0.75
    ocene
    -0.73
    izont
    -0.72
    pill
    -0.71
    ãĤ´ãĥ³
    -0.70
    aturally
    -0.70
    cosystem
    -0.64
    pec
    -0.63
    POSITIVE LOGITS
     although
    0.88
     they
    0.85
    soever
    0.74
     there
    0.70
     '[
    0.68
     "[
    0.65
     he
    0.63
     whilst
    0.62
     we
    0.61
     she
    0.60
    Activations Density 0.200%

    No Known Activations