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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 10706
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions and related terms such as years and official sites

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and their affiliations

    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
    ãĥķãĤ©
    -0.83
    ãĥķãĤ¡
    -0.81
    ãĥĵ
    -0.79
    20439
    -0.77
    awk
    -0.70
    yout
    -0.66
    west
    -0.66
    onia
    -0.65
    èª
    -0.64
    ãĥ¼ãĤ¯
    -0.64
    POSITIVE LOGITS
     consume
    0.67
    ucer
    0.59
    ulet
    0.56
     hers
    0.56
     cutter
    0.55
     Destination
    0.55
    ariat
    0.55
     holder
    0.54
     targ
    0.54
     expend
    0.54
    Activations Density 0.217%

    No Known Activations