© 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. 11115
    Prev
    Next
    INDEX
    Explanations

    descriptions of a person's skills and qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject's characteristics and skills

    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
    ORY
    -0.67
     Millennium
    -0.66
     Seym
    -0.66
    endment
    -0.63
     Mandatory
    -0.62
    Untitled
    -0.62
    veyard
    -0.62
     leftover
    -0.59
     spurious
    -0.59
     Continuing
    -0.58
    POSITIVE LOGITS
     possesses
    1.38
     loves
    1.37
     prefers
    1.33
     enjoys
    1.31
     wears
    1.29
     knows
    1.26
     tends
    1.25
     lacks
    1.19
     hates
    1.19
     excel
    1.19
    Activations Density 0.211%

    No Known Activations