© 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. 1-RES-JB
    11. 9521
    Prev
    Next
    INDEX
    Explanations

    phrases related to size or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "big" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.87
     Emin
    -0.68
     Wake
    -0.67
     confir
    -0.66
    idency
    -0.66
     Examiner
    -0.65
     Lauder
    -0.65
    åĤ
    -0.65
    OCK
    -0.62
    Dialogue
    -0.61
    POSITIVE LOGITS
    gest
    1.34
    ger
    1.13
    big
    0.97
    glers
    0.86
    ging
    0.86
    oted
    0.84
    Boss
    0.83
    boss
    0.83
    gers
    0.82
    GER
    0.81
    Activations Density 0.009%

    No Known Activations