© 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. 24065
    Prev
    Next
    INDEX
    Explanations

    names of universities and other educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to emails and their validation

    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
    asio
    -0.59
    rained
    -0.53
    ment
    -0.51
    ahime
    -0.51
     retri
    -0.49
    Availability
    -0.48
     whenever
    -0.48
    apo
    -0.47
    ero
    -0.47
     time
    -0.47
    POSITIVE LOGITS
    sonian
    0.52
     enthusi
    0.52
     sqor
    0.49
    tering
    0.49
     metic
    0.48
    bi
    0.47
     livest
    0.46
     sacrific
    0.46
    mitted
    0.46
    olithic
    0.45
    Activations Density 0.335%

    No Known Activations