© 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. 24099
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality or attribution

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in various contexts

    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
     consolation
    -0.84
     Remastered
    -0.75
     weekly
    -0.72
     sav
    -0.71
     slightly
    -0.71
     upside
    -0.71
     Yen
    -0.71
     weekend
    -0.70
     resur
    -0.70
     retreat
    -0.69
    POSITIVE LOGITS
    such
    2.18
    including
    2.03
    especially
    1.81
    particularly
    1.80
    whether
    1.77
    typically
    1.77
    usually
    1.76
    excluding
    1.73
    often
    1.70
    except
    1.69
    Activations Density 0.148%

    No Known Activations