© 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. 8-RES-JB
    11. 702
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a position or location within a range or spectrum

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or a range of possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©Ł
    -0.72
    acas
    -0.65
     Doodle
    -0.63
    Rated
    -0.61
    ãĤŃ
    -0.61
     abroad
    -0.60
    llor
    -0.60
    Register
    -0.60
    ãĢij
    -0.58
    Newsletter
    -0.58
    POSITIVE LOGITS
     coincidence
    1.08
     exaggeration
    0.89
     probabilities
    0.89
     extremes
    0.85
     possibilities
    0.81
     impossibility
    0.79
     guesses
    0.78
     scenarios
    0.77
     absurdity
    0.76
    depending
    0.76
    Activations Density 0.689%

    No Known Activations