© 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. 18509
    Prev
    Next
    INDEX
    Explanations

    phrases related to levels of measurement or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to high levels or rates of various phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    herer
    -0.79
    ãĤµ
    -0.72
    irit
    -0.70
    ulpt
    -0.69
    them
    -0.69
    Sham
    -0.68
    uphem
    -0.68
    ãĤ´ãĥ³
    -0.67
    apons
    -0.66
    tnc
    -0.66
    POSITIVE LOGITS
     percentage
    1.29
     rates
    1.24
     incidence
    1.21
     levels
    1.20
     percentages
    1.20
     prevalence
    1.19
     probability
    1.19
     likelihood
    1.14
     rate
    1.10
     amount
    1.09
    Activations Density 0.109%

    No Known Activations