© 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. 17588
    Prev
    Next
    INDEX
    Explanations

    specific letters, numbers, or words tagged with unique symbols such as figures, configuration options, or image layers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific labels, identifiers, or points of interest

    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
    mosp
    -0.68
    etimes
    -0.60
     lan
    -0.60
     oath
    -0.59
    tones
    -0.59
    doms
    -0.58
    âĸ¬
    -0.58
     deterrent
    -0.56
     Accountability
    -0.56
    TPPStreamerBot
    -0.56
    POSITIVE LOGITS
     onwards
    0.93
    above
    0.78
    002
    0.78
     onward
    0.75
     above
    0.73
    below
    0.72
    003
    0.71
    103
    0.70
     wherein
    0.70
    xxxx
    0.70
    Activations Density 0.144%

    No Known Activations