© 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. 11-RES-JB
    11. 16403
    Prev
    Next
    INDEX
    Explanations

    words indicating the perception or impact of something on individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of impact or effect being felt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adra
    -0.81
    ascript
    -0.76
    strate
    -0.75
    yne
    -0.75
    stellar
    -0.74
    Cod
    -0.74
    ctors
    -0.72
    lihood
    -0.72
    config
    -0.70
    adr
    -0.68
    POSITIVE LOGITS
     brunt
    1.36
     urge
    1.26
     effects
    1.24
     pinch
    1.16
     slightest
    1.16
     sting
    1.12
     need
    1.11
     compulsion
    1.09
     same
    1.08
     strain
    1.07
    Activations Density 0.080%

    No Known Activations