© 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. 0-RES-JB
    11. 16527
    Prev
    Next
    INDEX
    Explanations

    keywords related to compression

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adan
    -0.78
    sted
    -0.77
     Ally
    -0.75
    igil
    -0.75
     Muslim
    -0.74
    Role
    -0.74
     Ven
    -0.73
    rait
    -0.73
    itizens
    -0.73
    elligence
    -0.72
    POSITIVE LOGITS
     compression
    3.28
     compressed
    3.00
     decomp
    2.83
     compress
    2.81
     compressor
    2.33
     uncomp
    1.99
     JPEG
    1.30
     recomp
    1.26
     codec
    1.26
    gz
    1.23
    Activations Density 0.032%

    No Known Activations