© 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. 7150
    Prev
    Next
    INDEX
    Explanations

    instances where something is being added or included

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "addition."

    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
    bis
    -0.73
    bane
    -0.65
    ARDS
    -0.65
     Prediction
    -0.64
    generic
    -0.60
    meta
    -0.60
    ESE
    -0.59
     Neutral
    -0.59
    rics
    -0.58
    ollo
    -0.58
    POSITIVE LOGITS
    xual
    0.88
    ition
    0.83
    itious
    0.82
     thereto
    0.79
    endum
    0.74
    tions
    0.70
    ract
    0.70
     bonus
    0.70
    itive
    0.69
    itionally
    0.68
    Activations Density 0.015%

    No Known Activations