© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    terms related to technological aspects such as code, protocols, and features

    oai_token-act-pair · gpt-3.5-turbo

    recurring instances of the word "the" and other contextually significant terms

    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
    nces
    -0.73
    !.
    -0.72
     whereas
    -0.69
    .,
    -0.69
    .
    -0.69
    .''.
    -0.68
    .:
    -0.68
    ';
    -0.67
     because
    -0.67
    Joined
    -0.66
    POSITIVE LOGITS
     latter
    1.03
     nutshell
    0.78
     aforementioned
    0.77
     equation
    0.76
     operation
    0.65
     varies
    0.64
     experiment
    0.64
    ses
    0.63
     trio
    0.63
     offending
    0.63
    Activations Density 0.395%

    No Known Activations