© 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. 7-RES-JB
    11. 21565
    Prev
    Next
    INDEX
    Explanations

    special characters and specific sequences of characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of high anticipation or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacked
    -0.72
     ransom
    -0.71
     ratified
    -0.71
     negoti
    -0.71
     intercepted
    -0.71
     antit
    -0.69
     equivalent
    -0.69
     overth
    -0.68
     enshr
    -0.67
     hed
    -0.67
    POSITIVE LOGITS
    Anyway
    1.61
    My
    1.25
    Honestly
    1.17
    ³³³³
    1.16
    Personally
    1.15
    Thank
    1.15
    ³³³³³³³³³³³³³³³³
    1.14
    MY
    1.13
    I
    1.12
    ³³³
    1.11
    Activations Density 0.500%

    No Known Activations