© 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. 3-RES-JB
    11. 6513
    Prev
    Next
    INDEX
    Explanations

    terms related to colors, particularly shades of blue and red

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to colors or specific brands and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.71
    ioned
    -0.71
    Thomas
    -0.71
    nings
    -0.70
    HCR
    -0.70
    EMENT
    -0.69
    JECT
    -0.67
     ALSO
    -0.66
    isites
    -0.65
    WHERE
    -0.64
    POSITIVE LOGITS
     Cyan
    0.91
    ohydrate
    0.89
    ohyd
    0.83
    ophon
    0.83
    ogen
    0.81
    otic
    0.81
     iod
    0.81
    otech
    0.76
    urnal
    0.75
    omet
    0.75
    Activations Density 0.009%

    No Known Activations