© 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. 13469
    Prev
    Next
    INDEX
    Explanations

    dates formatted as dd/mm/yyyy

    oai_token-act-pair · gpt-3.5-turbo

    references to the number "19" 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
    aminer
    -0.85
    orc
    -0.77
    plom
    -0.77
    ellation
    -0.75
    igent
    -0.74
    endum
    -0.74
    ilic
    -0.72
    qqa
    -0.71
    ipment
    -0.71
    plings
    -0.71
    POSITIVE LOGITS
    th
    0.97
    âĸĪâĸĪ
    0.96
    61
    0.87
    05
    0.86
    07
    0.85
    09
    0.84
    87
    0.81
    03
    0.80
    eteenth
    0.80
    04
    0.79
    Activations Density 0.015%

    No Known Activations