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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 569
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.72
     Gaw
    -0.66
    coni
    -0.64
     Niet
    -0.64
     Moroc
    -0.64
     Vaugh
    -0.62
     convol
    -0.62
    attering
    -0.60
    licted
    -0.57
    akespe
    -0.57
    POSITIVE LOGITS
     RELEASE
    0.91
    ream
    0.59
    poses
    0.57
    ctive
    0.56
     inclusive
    0.56
     Released
    0.55
    externalActionCode
    0.54
    ISE
    0.53
    MEN
    0.52
     SHAR
    0.52
    Activations Density 0.167%

    No Known Activations