© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16623
    Prev
    Next
    INDEX
    Explanations

    words related to various types of -ologists and axioms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sociology and social sciences

    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
     Redux
    -0.72
     carn
    -0.67
     Events
    -0.63
     Femin
    -0.62
     transsexual
    -0.61
     nec
    -0.60
     staging
    -0.59
     decoration
    -0.59
     trolls
    -0.59
     Cats
    -0.59
    POSITIVE LOGITS
    iologist
    3.56
    iom
    1.96
    i
    1.71
    ipl
    1.44
    iator
    1.43
    iard
    1.31
    iov
    1.22
    unci
    1.19
    iasm
    1.07
    iop
    1.06
    Activations Density 0.030%

    No Known Activations