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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7252
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking time off or away from a situation

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating actions or relationships involving time and space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chell
    -0.65
    ivities
    -0.58
    iverse
    -0.55
    ickr
    -0.54
    odynamic
    -0.53
    Anonymous
    -0.53
    olitical
    -0.52
    hemer
    -0.51
    ciplinary
    -0.51
     teasp
    -0.51
    POSITIVE LOGITS
     behalf
    0.60
     Camel
    0.56
     either
    0.55
     rescuing
    0.54
     those
    0.52
    roads
    0.50
     both
    0.50
    orage
    0.49
    ij士
    0.49
     whichever
    0.48
    Activations Density 0.775%

    No Known Activations