© 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. 15639
    Prev
    Next
    INDEX
    Explanations

    terms related to potential threats or challenges

    oai_token-act-pair · gpt-3.5-turbo

    words associated with challenges or issues that need to be addressed

    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
    udeau
    -0.77
    ierre
    -0.76
    adier
    -0.76
    pan
    -0.76
    cipled
    -0.74
    atever
    -0.69
    itte
    -0.67
    ERAL
    -0.66
    PU
    -0.64
    aucus
    -0.63
    POSITIVE LOGITS
     therein
    0.85
     herein
    0.77
     plag
    0.72
     by
    0.71
    ocument
    0.71
     thereto
    0.68
     incidentally
    0.66
     esp
    0.66
    Ĥİ
    0.65
     emanating
    0.65
    Activations Density 0.335%

    No Known Activations