© 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. 11-RES-JB
    11. 22675
    Prev
    Next
    INDEX
    Explanations

    information related to numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and statistics

    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
     perspect
    -0.78
     advoc
    -0.74
     enthusi
    -0.71
     princ
    -0.69
     nodd
    -0.67
     philos
    -0.67
     duty
    -0.66
     conduc
    -0.66
     privileges
    -0.66
     corrections
    -0.65
    POSITIVE LOGITS
    5
    1.94
    6
    1.80
    8
    1.79
    7
    1.78
    4
    1.77
    3
    1.76
    9
    1.70
    2
    1.66
    1
    1.58
    75
    1.58
    Activations Density 0.059%

    No Known Activations