© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3232
    Prev
    Next
    INDEX
    Explanations

    questions related to preferences, opinions, or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional questions or hypothetical scenarios

    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
     dun
    -0.64
    è¦ļéĨĴ
    -0.61
    holder
    -0.61
    established
    -0.60
    meta
    -0.60
    noticed
    -0.58
    iser
    -0.57
    é¾įå
    -0.57
    Pie
    -0.57
    named
    -0.57
    POSITIVE LOGITS
     be
    0.79
     anyone
    0.77
     suffice
    0.77
     anybody
    0.76
     you
    0.73
    ĸļ
    0.72
     motivate
    0.71
     happen
    0.71
    nt
    0.71
     qualify
    0.70
    Activations Density 0.067%

    No Known Activations