© 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. 864
    Prev
    Next
    INDEX
    Explanations

    quantitative data presented as percentages or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages related to various topics

    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
     prelim
    -0.70
     tresp
    -0.64
     distance
    -0.63
     decor
    -0.62
    evin
    -0.62
     outdoors
    -0.61
     afar
    -0.60
     tension
    -0.59
    veland
    -0.59
    ilic
    -0.59
    POSITIVE LOGITS
     million
    1.29
     billion
    1.21
    %
    1.21
     trillion
    1.20
     percent
    1.17
    %"
    1.14
     lakh
    1.10
    %-
    1.07
    million
    1.07
    billion
    1.06
    Activations Density 0.324%

    No Known Activations