Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5853
    Prev
    Next
    INDEX
    Explanations

    words related to the action of emptying or leaving a place or a space

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vac" and its variations related to empty spaces or abandonment

    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
    xual
    -0.75
     Angus
    -0.73
    nings
    -0.69
    Downloadha
    -0.67
    vironment
    -0.66
    ¶ħ
    -0.66
    sth
    -0.65
    heimer
    -0.64
    wards
    -0.64
    trust
    -0.63
    POSITIVE LOGITS
    ancies
    1.04
     vac
    1.01
    entric
    0.98
     Vac
    0.82
    ourn
    0.79
     vacated
    0.74
    orem
    0.72
    oshenko
    0.71
    ancouver
    0.70
    apor
    0.70
    Activations Density 0.007%

    No Known Activations