© 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. 0-RES-JB
    11. 16467
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement upwards, particularly climbing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¸
    -0.71
     centers
    -0.70
     Innocent
    -0.68
    soType
    -0.65
    jad
    -0.65
    Products
    -0.64
    iov
    -0.63
    rex
    -0.63
    Express
    -0.63
     licensed
    -0.61
    POSITIVE LOGITS
     climb
    3.53
     climbs
    2.61
     climbed
    2.48
     climbing
    2.47
     ascent
    2.15
     climbers
    2.04
     ascend
    1.67
     hike
    1.58
     crawl
    1.53
     Clim
    1.43
    Activations Density 0.025%

    No Known Activations