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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 20558
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases that signify a successful or impactful outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases using metaphors related to "hitting" a target or achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iterator
    -0.66
    urdue
    -0.65
    ña
    -0.64
    lege
    -0.63
    wcsstore
    -0.63
    gio
    -0.63
    ocating
    -0.61
     Constantine
    -0.60
    umn
    -0.60
    shown
    -0.59
    POSITIVE LOGITS
     snag
    1.11
     stride
    1.11
     brakes
    1.01
     button
    0.93
     nail
    0.93
     milestones
    0.88
     hardest
    0.87
     itch
    0.86
     pavement
    0.82
     mark
    0.81
    Activations Density 0.155%

    No Known Activations