© 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. 9384
    Prev
    Next
    INDEX
    Explanations

    anecdotal evidence or anecdotes in text

    oai_token-act-pair · gpt-3.5-turbo

    references to anecdotal evidence and personal stories

    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
    ebus
    -0.98
    xual
    -0.82
    ktop
    -0.76
    ridges
    -0.76
    yss
    -0.76
    eering
    -0.76
    paces
    -0.73
    iasis
    -0.73
    abad
    -0.72
    hens
    -0.69
    POSITIVE LOGITS
     anecdotes
    1.17
     anecdotal
    1.14
     anecdote
    0.94
    è¦ļéĨĴ
    0.93
    RESULTS
    0.91
     anecd
    0.82
    odox
    0.77
     snapshots
    0.75
    ecd
    0.71
    evidence
    0.71
    Activations Density 0.019%

    No Known Activations