© 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. 6-RES-JB
    11. 1644
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to organizations or entities with the abbreviation 'HS'

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, specifically Humane Societies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.72
    verages
    -0.67
    stru
    -0.67
     Samoa
    -0.65
    circle
    -0.65
    bidden
    -0.65
    osi
    -0.64
    sett
    -0.63
    dylib
    -0.62
    ments
    -0.61
    POSITIVE LOGITS
    ocial
    1.06
    HS
    0.98
    IFT
    0.95
    ELF
    0.90
    INESS
    0.89
    Ds
    0.88
    sein
    0.86
    EMA
    0.85
    TERN
    0.85
    OME
    0.83
    Activations Density 0.025%

    No Known Activations