© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22635
    Prev
    Next
    INDEX
    Explanations

    the term 'colocalization'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hamm
    -0.85
    FP
    -0.75
     Waves
    -0.69
     Acting
    -0.67
     Shap
    -0.66
     Demand
    -0.66
    ENDED
    -0.65
     Amber
    -0.64
    ady
    -0.63
    OSH
    -0.62
    POSITIVE LOGITS
     col
    3.68
    col
    1.66
     colon
    1.51
    Col
    1.44
     Col
    1.44
     Colossus
    1.24
     COL
    1.21
    COL
    1.18
     bowel
    1.17
    Cola
    1.07
    Activations Density 0.021%

    No Known Activations