© 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. 14976
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical fasteners like bolts

    oai_token-act-pair · gpt-3.5-turbo

    references to bolts and fastening components

    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
    afort
    -0.81
    guyen
    -0.74
    ileged
    -0.71
    olulu
    -0.70
    atorium
    -0.70
    anasia
    -0.69
    iciary
    -0.69
    braska
    -0.69
    estial
    -0.69
    estine
    -0.68
    POSITIVE LOGITS
    bolt
    0.86
    oning
    0.78
    bol
    0.77
     bolts
    0.76
    combe
    0.71
    oute
    0.71
     cutter
    0.71
     upright
    0.71
     buckle
    0.70
    ucket
    0.69
    Activations Density 0.032%

    No Known Activations