© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    negative events or criticism

    oai_token-act-pair · gpt-3.5-turbo

    negative expressions or references to failure

    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
     Salvador
    -0.70
     Samoa
    -0.69
     Nordic
    -0.69
     Crimson
    -0.68
     Uni
    -0.68
     Yugoslav
    -0.66
     HRC
    -0.66
     CBI
    -0.65
     Hels
    -0.65
     Marketable
    -0.65
    POSITIVE LOGITS
    based
    1.25
    level
    1.19
    mounted
    1.17
    goers
    1.16
    door
    1.14
    trained
    1.12
    loving
    1.10
    sized
    1.10
    building
    1.09
    training
    1.06
    Activations Density 0.074%

    No Known Activations