© 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. 18590
    Prev
    Next
    INDEX
    Explanations

    words related to dirt or grime

    oai_token-act-pair · gpt-3.5-turbo

    words starting with "gr" that relate to negative or undesirable qualities

    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
    -0.76
    vention
    -0.72
    hibition
    -0.71
    ership
    -0.68
    )=(
    -0.67
    idas
    -0.64
    PORT
    -0.63
    ARGET
    -0.62
    hire
    -0.62
     Doctrine
    -0.60
    POSITIVE LOGITS
    udge
    1.23
    umpy
    1.18
    udging
    1.11
    aciously
    1.10
    iddles
    1.06
    iddle
    1.05
    illing
    0.99
    ubb
    0.98
    itt
    0.97
    ubby
    0.97
    Activations Density 0.015%

    No Known Activations