© 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. 9271
    Prev
    Next
    INDEX
    Explanations

    terms related to the ability or potential of something to be fixed, cached, invested, or manipulated

    oai_token-act-pair · gpt-3.5-turbo

    words that signify capability or suitability for a specific action or circumstance

    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
    erva
    -0.88
    ffic
    -0.74
    umat
    -0.73
    OTO
    -0.72
    akedown
    -0.70
    vertisement
    -0.70
    acha
    -0.70
    itect
    -0.69
    achu
    -0.68
    krit
    -0.67
    POSITIVE LOGITS
     guid
    0.72
     qualities
    0.72
     trait
    0.70
    atable
    0.69
    lihood
    0.69
     flaw
    0.68
     commodity
    0.68
     starch
    0.68
     lapse
    0.67
     offence
    0.66
    Activations Density 0.098%

    No Known Activations