© 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. 11-RES-JB
    11. 10038
    Prev
    Next
    INDEX
    Explanations

    information related to negative consequences or dangers

    oai_token-act-pair · gpt-3.5-turbo

    themes related to moral ambiguity and human nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mentioning
    -0.59
     Pwr
    -0.56
     thats
    -0.56
     noting
    -0.56
     tho
    -0.55
     resear
    -0.54
     testament
    -0.54
     realise
    -0.53
     acknowledgement
    -0.53
     noted
    -0.52
    POSITIVE LOGITS
     impunity
    0.80
    lessly
    0.77
     unlawfully
    0.74
    uously
    0.69
     arbitrarily
    0.68
    ocr
    0.67
     unfairly
    0.65
     inappropriately
    0.64
    itarian
    0.63
    versive
    0.62
    Activations Density 0.698%

    No Known Activations