© 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. 11092
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to actions or items related to food and consumption

    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
    anamo
    -0.61
    agged
    -0.61
    ighed
    -0.58
    interstitial
    -0.56
    translation
    -0.55
     unaccount
    -0.54
     embroiled
    -0.54
    legates
    -0.51
     coron
    -0.51
    ocally
    -0.50
    POSITIVE LOGITS
     ASAP
    1.27
     yourselves
    1.26
     yourself
    1.26
     wisely
    1.20
     preferably
    1.19
    !
    1.11
    !:
    1.06
     ;)
    1.04
     Yourself
    1.02
     BEFORE
    1.02
    Activations Density 0.592%

    No Known Activations