© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    comparative statements involving quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that indicate something is greater than another

    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
    ilic
    -0.74
    ctive
    -0.73
    oft
    -0.70
    limited
    -0.68
    alf
    -0.68
    atis
    -0.66
    itis
    -0.66
    Creat
    -0.66
    agn
    -0.64
    ãĥŁ
    -0.63
    POSITIVE LOGITS
     doubling
    0.97
     tripled
    0.95
     doubled
    0.91
     twice
    0.84
     half
    0.73
    racuse
    0.72
     expected
    0.70
    lihood
    0.68
     compensated
    0.67
     400
    0.66
    Activations Density 0.093%

    No Known Activations