© 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. 2-RES-JB
    11. 12940
    Prev
    Next
    INDEX
    Explanations

    references to specific street names or locations, particularly ones involving the word 'Mill'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mill" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offending
    -0.67
     coordinated
    -0.67
     prone
    -0.66
     effected
    -0.65
     compr
    -0.65
     familiar
    -0.64
     manifest
    -0.64
    ----------------------------------------------------------------
    -0.64
     ACTION
    -0.64
     compelling
    -0.63
    POSITIVE LOGITS
    enium
    1.62
    imet
    1.16
    igans
    1.13
    isec
    1.13
    enn
    1.03
    itary
    1.03
    imeter
    1.03
    icent
    1.02
    imeters
    0.98
    stones
    0.97
    Activations Density 0.003%

    No Known Activations