© 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. 3-RES-JB
    11. 15043
    Prev
    Next
    INDEX
    Explanations

    certain recurring patterns of characters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to familial or relational roles, particularly 'hen' and 'tom,' which signify gendered familial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.84
     Simulator
    -0.82
     Index
    -0.74
     Station
    -0.73
     Keys
    -0.72
    HAM
    -0.71
    Reference
    -0.71
     Retail
    -0.70
     Disorder
    -0.69
     Solution
    -0.69
    POSITIVE LOGITS
    ials
    0.92
    iably
    0.81
    gee
    0.81
    icular
    0.74
    etime
    0.73
    iatrics
    0.72
    aciously
    0.72
     bron
    0.71
    ucl
    0.70
    itely
    0.70
    Activations Density 0.035%

    No Known Activations