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. 1-RES-JB
    6. 19484
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or problems

    oai_token-act-pair · gpt-3.5-turbo

    articles and certain prepositions in a sentence

    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
    RAM
    -0.76
    obyl
    -0.71
     sshd
    -0.70
    hra
    -0.68
    prints
    -0.68
    akov
    -0.68
    OUP
    -0.67
    chall
    -0.65
    tel
    -0.65
    Hart
    -0.65
    POSITIVE LOGITS
     Celeb
    0.69
     Osiris
    0.66
     respecting
    0.65
    entimes
    0.65
     controlling
    0.64
     buried
    0.62
     masse
    0.62
     Kardashian
    0.61
     woodland
    0.61
    natureconservancy
    0.60
    Activations Density 0.000%

    No Known Activations