© 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. 24151
    Prev
    Next
    INDEX
    Explanations

    names (especially "Neal") within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Neal" in various 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
    teen
    -0.83
    76561
    -0.73
    fare
    -0.73
    smoking
    -0.67
    stood
    -0.67
    coord
    -0.67
    UID
    -0.66
    exempt
    -0.65
    fully
    -0.64
     scant
    -0.64
    POSITIVE LOGITS
     Neal
    1.23
     Stephenson
    0.97
    Neal
    0.87
     Dickinson
    0.86
     Howe
    0.81
     Thomson
    0.77
    ison
    0.77
     Irwin
    0.77
     Adams
    0.76
     Harrington
    0.76
    Activations Density 0.004%

    No Known Activations