© 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. 0-RES-JB
    11. 12139
    Prev
    Next
    INDEX
    Explanations

    words related to gaining access or permission to enter a place or a group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "entry" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arse
    -0.71
    usat
    -0.68
    wu
    -0.66
    âĻ¥
    -0.65
    iven
    -0.63
    paren
    -0.62
     Cord
    -0.60
    ðŁĺ
    -0.60
    onies
    -0.60
    bara
    -0.59
    POSITIVE LOGITS
     entry
    3.97
     Entry
    2.89
     entries
    2.60
    Entry
    2.36
    entry
    2.12
     entrance
    2.00
     admission
    1.70
     entrants
    1.69
     passage
    1.33
     exit
    1.27
    Activations Density 0.008%

    No Known Activations