© 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. 7-RES-JB
    11. 15702
    Prev
    Next
    INDEX
    Explanations

    phrases related to human expressions and interactions

    oai_token-act-pair · gpt-3.5-turbo

    capital letters and punctuation, indicating emphasis or titles

    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
     formerly
    -0.70
     Presence
    -0.70
     BMC
    -0.67
     Proceedings
    -0.65
     occupation
    -0.65
     influential
    -0.64
     accessible
    -0.63
    senal
    -0.63
     effective
    -0.63
     NCT
    -0.62
    POSITIVE LOGITS
    oooo
    1.42
    aaaa
    1.29
    mmmm
    1.28
    oooooooo
    1.21
    eeee
    1.19
    OOOO
    1.18
    EEEE
    1.15
    OOOOOOOO
    1.15
    mmm
    1.14
    ooo
    1.12
    Activations Density 0.346%

    No Known Activations