© 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. 4-RES-JB
    11. 7622
    Prev
    Next
    INDEX
    Explanations

    estimates of various quantities or values

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate estimated quantities or statistics

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

    No Comments

    Negative Logits
    woods
    -0.81
    feeding
    -0.80
    marine
    -0.76
    bub
    -0.74
    neys
    -0.74
    washer
    -0.72
    wood
    -0.70
    eland
    -0.69
    matter
    -0.69
    Interstitial
    -0.68
    POSITIVE LOGITS
     estimates
    0.92
    imate
    0.86
    imates
    0.83
     estimate
    0.78
     estimated
    0.78
     approximate
    0.74
     elapsed
    0.72
    imated
    0.69
     estimating
    0.69
     Estimates
    0.69
    Activations Density 0.023%

    No Known Activations