© 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. 9941
    Prev
    Next
    INDEX
    Explanations

    organizations or entities mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or institutions involved in social or political issues

    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
     therein
    -0.75
     elsewhere
    -0.75
    _.
    -0.64
    ''.
    -0.55
    ".
    -0.55
    Offline
    -0.52
    .</
    -0.52
    .''.
    -0.51
    '.
    -0.51
    .''
    -0.48
    POSITIVE LOGITS
     of
    0.55
    of
    0.54
    DragonMagazine
    0.54
    quartered
    0.49
    loads
    0.48
     OF
    0.48
    uga
    0.47
    enhagen
    0.46
     Of
    0.46
    ãĥ»
    0.46
    Activations Density 1.332%

    No Known Activations