© 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. 7302
    Prev
    Next
    INDEX
    Explanations

    verbs related to guidance, control, or direction

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "steer" and its variations in various contexts

    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
     residue
    -0.68
    NetMessage
    -0.65
     subsequ
    -0.64
    ples
    -0.64
    endment
    -0.64
     Ming
    -0.63
     Leban
    -0.63
    etition
    -0.62
    ossibility
    -0.61
    onial
    -0.61
    POSITIVE LOGITS
    acles
    0.87
     steer
    0.86
    age
    0.86
    nel
    0.83
    al
    0.82
    ALT
    0.79
    alties
    0.77
    sted
    0.76
    acon
    0.76
    ald
    0.75
    Activations Density 0.019%

    No Known Activations