© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    phrases related to the titles of things such as books, movies, and series

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    poke
    -0.65
    dding
    -0.62
    %]
    -0.62
    natureconservancy
    -0.60
    udding
    -0.60
    onica
    -0.60
    ħĭ
    -0.60
    weak
    -0.59
    NULL
    -0.59
    cking
    -0.58
    POSITIVE LOGITS
     consists
    1.52
     consisted
    1.36
     comprises
    1.33
     includes
    1.32
     contains
    1.29
     involves
    1.24
     corresponds
    1.16
     lasted
    1.15
     incorporates
    1.14
     represents
    1.13
    Activations Density 0.175%

    No Known Activations