© 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. 9425
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named John Sayles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Say" 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
     fullest
    -0.74
    emetery
    -0.74
    DERR
    -0.70
     conflic
    -0.66
     heels
    -0.66
    aceous
    -0.65
    âĨ
    -0.64
     climax
    -0.64
    abwe
    -0.63
    OGR
    -0.63
    POSITIVE LOGITS
     Say
    1.24
     goodbye
    1.05
    Say
    0.95
    renheit
    0.94
    enger
    0.92
    soever
    0.89
     Goodbye
    0.87
     hello
    0.81
    lihood
    0.79
    ings
    0.78
    Activations Density 0.008%

    No Known Activations