© 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. 7-RES-JB
    11. 8536
    Prev
    Next
    INDEX
    Explanations

    words related to people or entities named "Kell" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Kell" and its variations in contexts related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.71
     faint
    -0.67
     congr
    -0.63
     slightest
    -0.61
     Gemini
    -0.59
    */(
    -0.59
     controlling
    -0.58
     prec
    -0.58
     Carbuncle
    -0.57
     Emirates
    -0.57
    POSITIVE LOGITS
    ogg
    1.01
    erman
    0.93
    win
    0.84
    amine
    0.84
    seys
    0.83
    mare
    0.83
    ows
    0.81
    enberg
    0.81
    bye
    0.81
    yn
    0.79
    Activations Density 0.044%

    No Known Activations