© 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. 16439
    Prev
    Next
    INDEX
    Explanations

    numbers at the end of sentences

    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
     Schw
    -0.67
     yawn
    -0.65
    ienne
    -0.63
     bond
    -0.63
     chant
    -0.60
     Amen
    -0.60
     chants
    -0.60
     closer
    -0.59
     trough
    -0.59
     buzz
    -0.58
    POSITIVE LOGITS
    64
    3.46
    32
    2.18
    66
    2.03
    63
    1.98
    65
    1.97
    68
    1.91
    62
    1.78
    67
    1.72
    69
    1.72
    84
    1.72
    Activations Density 0.020%

    No Known Activations