© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14800
    Prev
    Next
    INDEX
    Explanations

    numbers presented in a specific format: a digit followed by a dash and another digit

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    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
    rame
    -0.63
     destro
    -0.61
    agna
    -0.57
    ourt
    -0.57
     forcefully
    -0.57
    TeX
    -0.57
     newsp
    -0.57
    ilic
    -0.57
    legal
    -0.57
    Ħ¢
    -0.56
    POSITIVE LOGITS
    %;
    1.06
     pts
    1.01
    %:
    0.96
    %,
    0.94
     Votes
    0.88
     (-
    0.87
     [+
    0.85
    %-
    0.84
    %
    0.84
     wins
    0.78
    Activations Density 0.164%

    No Known Activations