© 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. 19899
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tape"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tape."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Kingdoms
    -0.69
     Nev
    -0.64
     Feder
    -0.62
    quickShipAvailable
    -0.62
    Lv
    -0.62
    immune
    -0.60
     Nav
    -0.59
     Ign
    -0.59
    ãĥį
    -0.58
    public
    -0.58
    POSITIVE LOGITS
     tape
    4.12
     Tape
    3.19
     tapes
    2.92
     taped
    2.19
     videot
    1.96
     cassette
    1.82
     clip
    1.33
     clips
    1.28
     film
    1.26
     recording
    1.24
    Activations Density 0.016%

    No Known Activations