© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3930
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    references to bulk quantities or collections

    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
     Daisy
    -0.68
    ellen
    -0.67
     Wiley
    -0.67
     Roe
    -0.66
    İĭ
    -0.64
     Judges
    -0.64
    ĪĴ
    -0.61
     Rockefeller
    -0.61
     Piano
    -0.60
     Pere
    -0.60
    POSITIVE LOGITS
    heads
    1.07
    head
    0.98
    ier
    0.94
    iness
    0.89
    iest
    0.80
     quantities
    0.77
    haul
    0.75
    aging
    0.75
     bulk
    0.74
    shaw
    0.73
    Activations Density 0.036%

    No Known Activations