© 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. 17406
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing negative effects or harm

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causality and the effects of actions or events

    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
    stra
    -0.76
    sonian
    -0.70
    zb
    -0.69
     Rated
    -0.67
    ature
    -0.67
     Marketable
    -0.67
    nesday
    -0.67
     Introdu
    -0.66
    itsch
    -0.66
    ramid
    -0.66
    POSITIVE LOGITS
     havoc
    1.47
     headaches
    1.21
     confusion
    1.16
     mayhem
    1.15
     trouble
    1.14
     problems
    1.06
     panic
    1.04
     undue
    1.01
     irreversible
    0.98
     irritation
    0.98
    Activations Density 0.054%

    No Known Activations