© 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. 0-RES-JB
    11. 1190
    Prev
    Next
    INDEX
    Explanations

    references to various types of crews working on different tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of crews involved in different activities or operations

    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
    ret
    -0.71
     eBook
    -0.71
    idge
    -0.66
     Rand
    -0.64
     Speech
    -0.64
     Lect
    -0.64
    angible
    -0.63
    jew
    -0.63
    anta
    -0.62
     constitution
    -0.62
    POSITIVE LOGITS
     crews
    3.76
    Crew
    1.74
     fleets
    1.50
    crew
    1.49
     squads
    1.46
     technicians
    1.42
     gangs
    1.41
     rosters
    1.35
     Crew
    1.34
     teams
    1.33
    Activations Density 0.033%

    No Known Activations