© 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. 10-RES-JB
    11. 9318
    Prev
    Next
    INDEX
    Explanations

    mention of specific politicians, particularly representatives and ministers, in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to representatives in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underpin
    -0.78
     hem
    -0.70
    istically
    -0.67
     factor
    -0.66
    glers
    -0.65
     factors
    -0.64
    DragonMagazine
    -0.64
     hemisphere
    -0.63
     bul
    -0.63
     nature
    -0.63
    POSITIVE LOGITS
    orters
    1.45
    orter
    1.41
    utation
    1.23
    rint
    1.21
    ository
    1.19
    atri
    1.15
    rieve
    1.13
    ublic
    1.11
    utable
    1.11
    orted
    1.10
    Activations Density 0.016%

    No Known Activations