© 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. 7-RES-JB
    11. 7180
    Prev
    Next
    INDEX
    Explanations

    adjectives with negative connotations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bull
    -0.66
     Finder
    -0.62
     Ll
    -0.61
     Butt
    -0.58
     Knights
    -0.58
     Piano
    -0.57
     Christy
    -0.56
     Thirty
    -0.56
     Pyramid
    -0.56
    BSD
    -0.56
    POSITIVE LOGITS
    itably
    1.03
    oused
    1.02
    ousing
    0.96
    uates
    0.91
    ously
    0.88
    mented
    0.86
    olves
    0.86
    ased
    0.85
    anced
    0.84
    uted
    0.84
    Activations Density 0.149%

    No Known Activations