© 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. 8-RES-JB
    11. 22426
    Prev
    Next
    INDEX
    Explanations

    phrases related to information provided under specific conditions or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to conditions, particularly in relation to anonymity or circumstances around spoken information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vantage
    -0.72
    thal
    -0.66
    kil
    -0.64
     Silver
    -0.61
    û
    -0.61
    issance
    -0.60
    ils
    -0.59
    Dust
    -0.58
    Spot
    -0.58
     Scholar
    -0.57
    POSITIVE LOGITS
     anonymity
    0.73
    aldehyde
    0.70
     agreeing
    0.67
     permission
    0.66
     guaranteeing
    0.66
     surrender
    0.65
    taker
    0.64
     assurances
    0.64
    arial
    0.63
     authorization
    0.63
    Activations Density 0.019%

    No Known Activations