© 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. 16842
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reports and political figures

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of "Rep", likely indicating a focus on political representatives or representatives in a context

    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
    glers
    -0.73
    GGGGGGGG
    -0.67
    istically
    -0.65
    phal
    -0.64
    FACE
    -0.61
     Keane
    -0.61
    IAS
    -0.61
     FORM
    -0.60
     Gauntlet
    -0.59
    BuyableInstoreAndOnline
    -0.59
    POSITIVE LOGITS
    rint
    1.21
    orted
    1.08
    resa
    1.00
    ository
    0.99
    orter
    0.95
    ublic
    0.91
     ancest
    0.91
    ositories
    0.91
    rodu
    0.91
    orters
    0.88
    Activations Density 0.006%

    No Known Activations