© 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. 16414
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "Combined" along with additional related context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combined" 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
     Passage
    -0.81
    irez
    -0.77
    keeper
    -0.77
    endez
    -0.76
    holes
    -0.74
    psc
    -0.71
    article
    -0.71
    ety
    -0.70
    ond
    -0.69
    gins
    -0.68
    POSITIVE LOGITS
     efforts
    0.75
     effort
    0.72
    ãĤ¤ãĥĪ
    0.70
     forces
    0.68
     totals
    0.66
     effects
    0.65
    inations
    0.65
     force
    0.62
     editions
    0.61
     with
    0.60
    Activations Density 0.036%

    No Known Activations