© 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. 22208
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence of change or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or the concept of "nothing."

    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
    ahime
    -0.76
    rences
    -0.62
     encountering
    -0.62
     AX
    -0.61
    lance
    -0.59
     fielding
    -0.59
    lr
    -0.57
     face
    -0.57
     boarding
    -0.56
    avia
    -0.55
    POSITIVE LOGITS
    except
    0.83
    imilar
    0.81
    wrong
    0.75
     resembling
    0.74
    Changed
    0.74
     wrong
    0.72
    atan
    0.71
     changed
    0.70
    pleasant
    0.68
    Except
    0.67
    Activations Density 0.182%

    No Known Activations