© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    phrases related to editorial positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of editorial positions or titles

    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
     Dull
    -0.78
     Pryor
    -0.75
     Hemp
    -0.71
     Arrow
    -0.70
     Cotton
    -0.70
     Downs
    -0.68
     Dunk
    -0.68
     Helic
    -0.67
     hots
    -0.66
     Stun
    -0.66
    POSITIVE LOGITS
    turned
    1.58
    general
    1.45
    cum
    1.29
    tre
    1.27
    design
    1.25
    scient
    1.19
    operator
    1.19
    General
    1.18
    director
    1.18
    elect
    1.16
    Activations Density 0.046%

    No Known Activations