© 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. 7-RES-JB
    11. 3088
    Prev
    Next
    INDEX
    Explanations

    symbols used as separators in text

    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
    ozyg
    -0.79
     gobl
    -0.71
    ikuman
    -0.69
     defe
    -0.65
     cellar
    -0.64
    emaker
    -0.64
     estab
    -0.63
    idth
    -0.63
     aborted
    -0.62
     involuntary
    -0.62
    POSITIVE LOGITS
     Both
    1.21
     These
    1.21
     Also
    1.20
     Together
    1.18
     Additionally
    1.16
     Each
    1.14
     Basically
    1.11
     They
    1.10
     Those
    1.06
     respectively
    1.03
    Activations Density 0.603%

    No Known Activations