© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3455
    Prev
    Next
    INDEX
    Explanations

    names of specific places or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names or places

    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
    izoph
    -0.80
     fundament
    -0.72
    ews
    -0.70
    stice
    -0.70
     Runes
    -0.70
     univers
    -0.69
    afety
    -0.67
     persisted
    -0.65
    ingham
    -0.65
     Awareness
    -0.64
    POSITIVE LOGITS
    late
    0.72
    ŃĶ
    0.70
    riot
    0.67
    NetMessage
    0.65
     assailants
    0.64
    okia
    0.64
    omination
    0.63
    boys
    0.63
    rival
    0.62
    bed
    0.62
    Activations Density 0.000%

    No Known Activations