© 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. 1-RES-JB
    11. 3247
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or governmental/political actions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating ongoing or completed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itness
    -0.69
    asty
    -0.61
     amen
    -0.60
     outcry
    -0.57
    poke
    -0.57
     impulse
    -0.56
    urry
    -0.56
    eve
    -0.56
    right
    -0.55
     idi
    -0.55
    POSITIVE LOGITS
    ĸļ
    1.04
    senal
    0.90
    bourg
    0.86
    enegger
    0.80
    gerald
    0.78
    raltar
    0.77
    è£ħ
    0.72
    metics
    0.72
    verages
    0.71
    thumbnails
    0.69
    Activations Density 1.779%

    No Known Activations