© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4569
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions in a hierarchy or physical positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to position or placement, specifically "back" and "front" in various contexts

    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
    alach
    -0.78
    ritch
    -0.73
    phis
    -0.73
    thood
    -0.68
    lectic
    -0.66
    anmar
    -0.65
    atown
    -0.65
    upon
    -0.64
    emouth
    -0.63
    ĸļ
    -0.61
    POSITIVE LOGITS
     heels
    0.96
     occasions
    0.93
     basis
    0.92
     side
    0.89
    ilts
    0.87
     shelf
    0.86
     sidelines
    0.86
     occasion
    0.83
    ieth
    0.82
     grounds
    0.82
    Activations Density 0.146%

    No Known Activations