© 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. 22569
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables and functions

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and notations used in equations

    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
     sponsor
    -0.72
     intent
    -0.72
     stockpile
    -0.71
     improvised
    -0.71
     rehears
    -0.70
     timed
    -0.69
     chats
    -0.69
     stockp
    -0.68
     reservations
    -0.68
     unprepared
    -0.68
    POSITIVE LOGITS
    ^{
    1.97
    _{
    1.89
    {\
    1.66
    }}
    1.64
    }\
    1.64
    \)
    1.58
     {\
    1.55
    }}}
    1.55
    $$
    1.51
    }{
    1.46
    Activations Density 0.036%

    No Known Activations