© 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. 11568
    Prev
    Next
    INDEX
    Explanations

    words related to unity or togetherness

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'u'

    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
     EDITION
    -0.60
     endeavors
    -0.57
     Opportunity
    -0.57
     equally
    -0.55
     fairness
    -0.55
     editions
    -0.55
     Forever
    -0.55
     printing
    -0.54
     Tenth
    -0.54
     Bones
    -0.54
    POSITIVE LOGITS
    u
    3.93
    ua
    1.89
    uin
    1.80
    ui
    1.64
    uj
    1.63
    uer
    1.63
    uo
    1.63
    uv
    1.61
    uity
    1.61
    uu
    1.56
    Activations Density 0.027%

    No Known Activations