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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 23635
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ro" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     iPod
    -0.77
     amulet
    -0.73
     diver
    -0.71
     bearer
    -0.70
     accum
    -0.69
     som
    -0.69
     confused
    -0.68
     synth
    -0.66
     fatig
    -0.65
     clones
    -0.65
    POSITIVE LOGITS
    Ro
    3.71
     Rooney
    2.35
     Roose
    1.61
     Roof
    1.57
     Ro
    1.40
    Ry
    1.26
    Ko
    1.20
    Sa
    1.12
     Roosevelt
    1.09
    RO
    1.08
    Activations Density 0.034%

    No Known Activations