© 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. 11-RES-JB
    11. 6588
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or steps to take

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of togetherness or unity

    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
    pse
    -0.47
     outburst
    -0.47
    sov
    -0.46
     Enhancement
    -0.44
    best
    -0.44
     hordes
    -0.43
     Redux
    -0.43
    thing
    -0.43
    eport
    -0.42
    etheus
    -0.42
    POSITIVE LOGITS
    ++)
    0.63
    ]);
    0.56
     trusting
    0.55
     comfortable
    0.52
    dL
    0.52
    nosis
    0.51
    cas
    0.50
    ));
    0.49
    pret
    0.49
    imate
    0.48
    Activations Density 0.843%

    No Known Activations