© 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. 10-RES-JB
    11. 7884
    Prev
    Next
    INDEX
    Explanations

    references to news, events, or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to serious incidents or events, particularly those involving death or risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slurs
    -0.67
     slut
    -0.64
    pmwiki
    -0.63
     trolls
    -0.60
     whistleblowers
    -0.58
     comedians
    -0.57
     pals
    -0.57
     rappers
    -0.56
     squirrel
    -0.56
     plaint
    -0.56
    POSITIVE LOGITS
    ufact
    0.76
    chnology
    0.64
    sequently
    0.63
     timeframe
    0.61
     Europe
    0.60
    olution
    0.57
    ructure
    0.57
    Secondly
    0.55
    existing
    0.55
     previous
    0.55
    Activations Density 1.379%

    No Known Activations