© 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. 19942
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to abstraction

    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
    ocked
    -0.77
    era
    -0.74
    ocking
    -0.72
    dor
    -0.72
     tipped
    -0.72
    fired
    -0.71
    fire
    -0.70
    ugh
    -0.69
     Bet
    -0.69
    luck
    -0.67
    POSITIVE LOGITS
     abstract
    3.84
     Abstract
    2.59
    stract
    2.52
     abstraction
    2.36
    Abstract
    2.04
     algebra
    1.11
     intangible
    1.08
     conceptual
    1.06
     aggregate
    1.04
     geometric
    0.97
    Activations Density 0.019%

    No Known Activations