© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    time expressions in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    repeated numerical values or identifiers related to a specific event or dataset

    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
    ascus
    -0.97
    hers
    -0.91
    nesday
    -0.89
    undai
    -0.88
    cles
    -0.86
    ¥ŀ
    -0.84
    Reviewer
    -0.83
    raltar
    -0.83
    gewater
    -0.77
    nesota
    -0.76
    POSITIVE LOGITS
    678
    1.10
     ILCS
    0.93
    45
    0.90
    âĸijâĸij
    0.85
    67
    0.84
    345
    0.83
    44
    0.78
    41
    0.78
    rpm
    0.77
    42
    0.76
    Activations Density 0.016%

    No Known Activations