© 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. 4-RES-JB
    11. 22650
    Prev
    Next
    INDEX
    Explanations

    conjunctions signaling alternatives

    oai_token-act-pair · gpt-3.5-turbo

    alternative options or comparisons

    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
    ires
    -0.71
    onday
    -0.67
    ELF
    -0.67
    efer
    -0.65
    emouth
    -0.63
    successfully
    -0.63
    hes
    -0.62
    Alert
    -0.62
    istors
    -0.61
    ptoms
    -0.61
    POSITIVE LOGITS
    acle
    1.48
    acles
    1.40
    Else
    1.29
    chard
    1.26
    ifice
    1.23
    chid
    1.16
    acular
    1.13
    nam
    1.13
    ific
    1.12
    lando
    1.12
    Activations Density 0.176%

    No Known Activations