© 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. 16345
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or terms likely associated with a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "hu" and its variations in different 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
    roller
    -0.68
    lined
    -0.67
    lining
    -0.66
    boards
    -0.65
    stay
    -0.64
    spin
    -0.63
     authorizing
    -0.62
    cloth
    -0.62
    turn
    -0.60
    Limited
    -0.60
    POSITIVE LOGITS
    awei
    1.67
    gey
    0.97
     Qiao
    0.96
    untled
    0.92
    azard
    0.92
    etz
    0.91
    isine
    0.91
     Zhu
    0.89
    jj
    0.87
    hu
    0.86
    Activations Density 0.008%

    No Known Activations