© 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. 10-RES-JB
    11. 6613
    Prev
    Next
    INDEX
    Explanations

    mentions of assessments or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" and its contextual variations within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.71
    untled
    -0.69
    llular
    -0.66
    leep
    -0.66
    awei
    -0.65
    iris
    -0.64
     lashed
    -0.62
     sacked
    -0.61
    assies
    -0.61
    etsk
    -0.60
    POSITIVE LOGITS
     hindsight
    1.37
     itself
    1.28
     retrospect
    1.23
     terms
    1.04
     disguise
    1.00
    asm
    0.97
     comparison
    0.96
     context
    0.94
    humane
    0.93
     spite
    0.87
    Activations Density 0.137%

    No Known Activations