© 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. 0-RES-JB
    11. 1061
    Prev
    Next
    INDEX
    Explanations

    descriptions and details of various entities or items

    oai_token-act-pair · gpt-3.5-turbo

    sections of a document that contain descriptions or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clot
    -0.70
    zig
    -0.65
     brick
    -0.62
     pag
    -0.62
    bledon
    -0.61
    aroo
    -0.61
    ven
    -0.60
    pez
    -0.59
    iard
    -0.59
    abal
    -0.59
    POSITIVE LOGITS
    Description
    3.41
    Details
    2.18
    description
    1.61
    Overview
    1.37
     Description
    1.26
    Features
    1.23
    Synopsis
    1.19
    Parameters
    1.18
    details
    1.09
    DES
    1.08
    Activations Density 0.028%

    No Known Activations