© 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. 11350
    Prev
    Next
    INDEX
    Explanations

    words related to news, information, and updates

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a text delimiter or end-of-text marker

    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
    éŃĶ
    -0.60
     incent
    -0.60
    legate
    -0.59
    ":""},{"
    -0.58
    æĥ
    -0.58
    çIJ
    -0.57
    è»
    -0.56
    NULL
    -0.56
    代
    -0.56
    uta
    -0.55
    POSITIVE LOGITS
     consequently
    0.79
     therefore
    0.79
    rogen
    0.77
    rogens
    0.77
     thus
    0.74
     then
    0.74
    /
    0.67
     hence
    0.67
     possibly
    0.66
     thence
    0.61
    Activations Density 0.537%

    No Known Activations