© 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. 9-RES-JB
    11. 18637
    Prev
    Next
    INDEX
    Explanations

    questions ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions about understanding implications and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toxin
    -0.69
     bul
    -0.66
    ality
    -0.66
    iannopoulos
    -0.65
    oki
    -0.65
    uther
    -0.65
     evening
    -0.65
     contr
    -0.64
    onte
    -0.63
     background
    -0.63
    POSITIVE LOGITS
     Well
    1.56
     Firstly
    1.35
     Probably
    1.31
     Quite
    1.29
     Answer
    1.23
     Certainly
    1.23
     Apparently
    1.22
     Possibly
    1.20
     Turns
    1.20
     Obviously
    1.20
    Activations Density 0.130%

    No Known Activations