© 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. 1-RES-JB
    11. 3317
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or metaphorical points of entry

    oai_token-act-pair · gpt-3.5-turbo

    references to "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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velength
    -0.68
    =-=-=-=-=-=-=-=-
    -0.67
    issance
    -0.66
    Downloadha
    -0.63
    Zip
    -0.62
     opio
    -0.62
     Archangel
    -0.61
     Balanced
    -0.61
     Carth
    -0.60
     Chill
    -0.60
    POSITIVE LOGITS
     entry
    1.21
     Entry
    1.02
     entries
    0.91
    entry
    0.87
    Entry
    0.84
    door
    0.75
     clearance
    0.74
    exit
    0.70
    ablishment
    0.70
     visas
    0.69
    Activations Density 0.006%

    No Known Activations