© 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. 8-RES-JB
    11. 5049
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce new sections or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Here" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sshd
    -0.62
     Archdemon
    -0.60
     Breath
    -0.58
    natureconservancy
    -0.58
    ONSORED
    -0.57
     absor
    -0.56
    uously
    -0.55
     actionGroup
    -0.54
    )].
    -0.53
     Strait
    -0.53
    POSITIVE LOGITS
    abouts
    1.29
    tics
    1.26
    tical
    1.23
    tic
    1.05
    after
    0.91
    upon
    0.86
    with
    0.84
    adays
    0.82
    fore
    0.80
     Comes
    0.80
    Activations Density 0.044%

    No Known Activations