Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21960
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "move" in various contexts

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

    No Comments

    Negative Logits
    omial
    -0.72
    sung
    -0.72
    oys
    -0.70
     sqor
    -0.68
    oured
    -0.66
    inges
    -0.64
    ingo
    -0.63
    culus
    -0.63
    iciency
    -0.61
    ongs
    -0.61
    POSITIVE LOGITS
     forward
    0.94
     toward
    0.86
    Motion
    0.80
     towards
    0.78
     away
    0.77
    brates
    0.76
     decisively
    0.75
    over
    0.70
     swiftly
    0.69
    overs
    0.67
    Activations Density 0.039%

    No Known Activations