© 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. 11-RES-JB
    11. 7019
    Prev
    Next
    INDEX
    Explanations

    words related to granting permission or authorization

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating permission or allowance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heads
    -0.66
    ened
    -0.66
    liest
    -0.66
    ord
    -0.65
    saw
    -0.65
    driver
    -0.65
     hates
    -0.64
    ening
    -0.64
    soDeliveryDate
    -0.64
    requires
    -0.64
    POSITIVE LOGITS
     flourish
    1.47
     thrive
    1.36
     prosper
    1.20
     remain
    1.19
     roam
    1.19
     continue
    1.19
     proceed
    1.18
     operate
    1.16
     prevail
    1.11
     slip
    1.11
    Activations Density 0.111%

    No Known Activations