© 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. 9-RES-JB
    11. 18558
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and terms like "more than", "overall", and "very happy"

    oai_token-act-pair · gpt-3.5-turbo

    evaluative language about film quality and enjoyment

    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
     contingency
    -0.84
     operatives
    -0.83
     hatched
    -0.78
     mosqu
    -0.75
     barric
    -0.73
     airspace
    -0.72
     communications
    -0.72
     mobilization
    -0.71
     parach
    -0.71
     lobbying
    -0.68
    POSITIVE LOGITS
     reviewer
    1.42
    Rating
    1.41
     reviewers
    1.33
     Rated
    1.30
    Reviewed
    1.28
    Review
    1.27
    Recommend
    1.22
    review
    1.21
     Rating
    1.15
    Score
    1.12
    Activations Density 0.906%

    No Known Activations