© 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. 8-RES-JB
    11. 7644
    Prev
    Next
    INDEX
    Explanations

    organizations or entities with specific characteristics mentioned in the context such as calendars, features, hidden features, review, and facility details

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to features and functionalities in a software or gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."[
    -0.91
    ).[
    -0.86
    .''
    -0.81
    ]."
    -0.79
    )."
    -0.79
     ÂŃ
    -0.78
    .")
    -0.73
    .</
    -0.72
    .'"
    -0.69
    ".[
    -0.69
    POSITIVE LOGITS
     POV
    0.85
     partName
    0.77
     Patreon
    0.72
     Hearth
    0.69
     FANTASY
    0.68
    prisingly
    0.68
     Edit
    0.65
    ':
    0.64
     huh
    0.64
     Appearance
    0.64
    Activations Density 1.825%

    No Known Activations