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. 6375
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific proper nouns and technical terms

    oai_token-act-pair · gpt-3.5-turbo
    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
    å§«
    -0.64
    )=(
    -0.63
    fetched
    -0.61
    awaru
    -0.60
    hots
    -0.58
     translates
    -0.56
    itars
    -0.55
     summed
    -0.54
    terday
    -0.53
     beware
    -0.53
    POSITIVE LOGITS
    osphere
    0.86
     ecosystem
    0.82
     universe
    0.79
     agenda
    0.78
     era
    0.75
     curriculum
    0.73
    agame
    0.73
     calendar
    0.72
     continuum
    0.72
    iverse
    0.71
    Activations Density 0.878%

    No Known Activations