© 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. 6-RES-JB
    11. 11601
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or names, specifically containing the pattern "Skid"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Skid" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.68
     merc
    -0.67
     cla
    -0.64
    emporary
    -0.62
    theless
    -0.62
    }}}
    -0.59
    hower
    -0.59
     sparse
    -0.58
     weakest
    -0.58
     fict
    -0.58
    POSITIVE LOGITS
    walker
    0.87
    addle
    0.83
    inski
    0.77
    kees
    0.76
    cheon
    0.76
    nik
    0.75
    ulkan
    0.75
    nit
    0.73
    DAQ
    0.73
    wagen
    0.72
    Activations Density 0.066%

    No Known Activations