© 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. 2-RES-JB
    11. 640
    Prev
    Next
    INDEX
    Explanations

    the word "Say" regardless of context

    oai_token-act-pair · gpt-4-turbo

    instances of the word "Say" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Say" in various forms or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abwe
    -0.80
    estern
    -0.75
    emetery
    -0.73
    ocaust
    -0.71
     fullest
    -0.70
    aceous
    -0.68
    culosis
    -0.67
    DERR
    -0.67
    ilaterally
    -0.66
    inges
    -0.65
    POSITIVE LOGITS
     Say
    1.11
     goodbye
    1.05
    enger
    0.89
     Goodbye
    0.86
     hello
    0.84
    ings
    0.82
    eed
    0.82
    Say
    0.81
    soever
    0.77
    y
    0.73
    Activations Density 0.014%

    No Known Activations