© 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. 2551
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What's the" or "What's the difference"

    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
    alde
    -0.88
    ornings
    -0.85
    mares
    -0.84
    cles
    -0.82
    chairs
    -0.81
    llers
    -0.81
    runners
    -0.77
    zes
    -0.76
    letes
    -0.75
    irms
    -0.74
    POSITIVE LOGITS
     significance
    1.11
     difference
    1.10
     rationale
    0.96
     extent
    0.95
     reperc
    0.94
     implication
    0.94
     implications
    0.92
     likelihood
    0.92
     relationship
    0.91
     purpose
    0.90
    Activations Density 0.067%

    No Known Activations