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. 6939
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or desire for action or possession

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential requirements or necessities

    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
     Asc
    -0.70
    uca
    -0.68
     Yosh
    -0.65
     IoT
    -0.63
     Vish
    -0.62
    azard
    -0.61
    uci
    -0.61
    Þ
    -0.61
    uum
    -0.61
    emetery
    -0.61
    POSITIVE LOGITS
     except
    0.79
    soever
    0.73
    illion
    0.71
     toget
    0.69
    except
    0.68
    rows
    0.68
     besides
    0.68
    points
    0.68
     hoop
    0.66
     fuss
    0.66
    Activations Density 0.131%

    No Known Activations