© 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. 924
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to levels or rates

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to comparative levels or risks, particularly those that indicate something is "higher" or "low."

    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
    ools
    -0.76
    sov
    -0.70
    emis
    -0.66
    RAW
    -0.66
    oral
    -0.65
    umbn
    -0.65
    ruction
    -0.63
    vice
    -0.61
    ellation
    -0.60
    atography
    -0.60
    POSITIVE LOGITS
     enough
    1.08
     compared
    1.05
     (>
    0.93
     proportion
    0.90
     (~
    0.84
     (<
    0.83
     relative
    0.82
     percentage
    0.80
     proport
    0.77
     proportions
    0.77
    Activations Density 0.117%

    No Known Activations