© 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. 7041
    Prev
    Next
    INDEX
    Explanations

    objects or terms related to handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "handles" in various contexts, particularly related to tools and physical objects

    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
    eatures
    -0.75
     Surveillance
    -0.67
    naire
    -0.64
     skies
    -0.64
    Republic
    -0.63
    ocument
    -0.63
     suites
    -0.62
     Aren
    -0.62
     accommodation
    -0.62
    vironment
    -0.62
    POSITIVE LOGITS
    bars
    1.04
    axe
    0.98
    pipe
    0.97
    gear
    0.97
     handle
    0.94
    lift
    0.94
    tails
    0.92
    handle
    0.90
    hammer
    0.88
    bridge
    0.86
    Activations Density 0.063%

    No Known Activations