© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1699
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a memorable impact or promise

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "will never" indicating strong negation or refusal

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

    No Comments

    Negative Logits
    lass
    -0.69
    urat
    -0.65
    toc
    -0.64
    het
    -0.64
    CAR
    -0.62
    raint
    -0.61
    ocard
    -0.61
    endar
    -0.61
    plates
    -0.60
     Creative
    -0.60
    POSITIVE LOGITS
    theless
    1.11
    icably
    0.86
     dreamed
    0.82
     stray
    0.81
     EVER
    0.78
     dream
    0.76
     achieve
    0.76
     underestimate
    0.74
     hesitate
    0.74
     dime
    0.73
    Activations Density 0.019%

    No Known Activations