© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11462
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal or political issues

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding significant incidents or allegations

    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
     ageing
    -0.95
     optim
    -0.86
     civilisation
    -0.84
     programmes
    -0.82
    anasia
    -0.80
     2050
    -0.76
     organise
    -0.76
     favour
    -0.75
    rowth
    -0.74
    population
    -0.73
    POSITIVE LOGITS
     redacted
    1.27
     allegations
    1.13
     allegation
    1.11
     bombshell
    1.10
     suspicious
    1.08
     corrobor
    1.06
     troubling
    1.04
     alleges
    1.03
     alleged
    1.01
     perjury
    1.00
    Activations Density 0.526%

    No Known Activations