© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    information or activities related to behind-the-scenes happenings

    oai_token-act-pair · gpt-3.5-turbo

    references to behind-the-scenes activities or situations

    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
    renheit
    -0.84
    haps
    -0.80
    vertisement
    -0.80
    imar
    -0.76
    ivia
    -0.75
    nesota
    -0.74
    ouple
    -0.73
    ighth
    -0.73
    ĭ
    -0.73
    olute
    -0.73
    POSITIVE LOGITS
     workings
    0.95
     dealings
    0.94
     operations
    0.86
     development
    0.85
     knowledge
    0.83
     mach
    0.82
     expertise
    0.78
     logistics
    0.78
     ops
    0.77
     operation
    0.76
    Activations Density 0.102%

    No Known Activations