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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 114
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions or behaviors related to following, playing, working, supporting, knowing, hearing, living, seeing, qualifying, opposing, coming up, trading, performing

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and beliefs of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.72
    iven
    -0.69
    HOW
    -0.69
    recy
    -0.67
    interstitial
    -0.64
    rison
    -0.63
    oney
    -0.63
    UNCH
    -0.62
    vity
    -0.60
    ERAL
    -0.59
    POSITIVE LOGITS
    pires
    0.85
     MFT
    0.69
    ":["
    0.67
    ophile
    0.67
    lege
    0.63
     Bonds
    0.62
    venant
    0.61
     Patron
    0.61
    eman
    0.60
     contrace
    0.60
    Activations Density 0.228%

    No Known Activations