© 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. 11698
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooperation and unity

    oai_token-act-pair · gpt-3.5-turbo

    references to operational functions or actions

    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
    ITED
    -0.66
     remnant
    -0.63
    WER
    -0.60
     Hann
    -0.59
     Yemeni
    -0.58
     gau
    -0.58
     restitution
    -0.58
     everlasting
    -0.57
     AGA
    -0.57
     embassy
    -0.57
    POSITIVE LOGITS
    op
    4.09
    ops
    2.46
    oped
    2.16
    opy
    2.04
    OP
    2.01
    opter
    1.96
    Op
    1.86
    oping
    1.84
    opa
    1.81
    opal
    1.66
    Activations Density 0.018%

    No Known Activations