© 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. 7689
    Prev
    Next
    INDEX
    Explanations

    words related to providing instructions or advice

    oai_token-act-pair · gpt-3.5-turbo

    references to guidance or instructions

    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
     Roses
    -0.75
     forfeit
    -0.73
    asts
    -0.73
    ells
    -0.72
    ols
    -0.68
     century
    -0.66
    Ve
    -0.66
     Biol
    -0.66
    parts
    -0.64
    WC
    -0.64
    POSITIVE LOGITS
     guidance
    1.35
     counselor
    1.07
     counselors
    1.01
     guideline
    0.96
     Guid
    0.93
     guidelines
    0.85
     guiding
    0.84
     guides
    0.81
     Advice
    0.78
    idelines
    0.77
    Activations Density 0.009%

    No Known Activations