© 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. 8600
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to secret or hidden information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "inner" in various contexts

    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
    atoes
    -0.86
    essors
    -0.80
    orthy
    -0.80
    enegger
    -0.78
    HAM
    -0.77
    netflix
    -0.75
    eday
    -0.74
    enance
    -0.73
    oulos
    -0.73
    HAHAHAHA
    -0.71
    POSITIVE LOGITS
     workings
    1.21
    most
    1.12
     sanct
    0.82
     inner
    0.78
     circle
    0.76
    ranean
    0.75
     circumference
    0.74
     combustion
    0.73
     turmoil
    0.73
    itud
    0.72
    Activations Density 0.009%

    No Known Activations