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. 24235
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions within sentences

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistical data within the text

    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
     marqu
    -0.70
    venge
    -0.69
     laundering
    -0.68
     pat
    -0.66
     splend
    -0.65
    ollah
    -0.65
    ylan
    -0.63
    hran
    -0.63
    Ü
    -0.63
     convoy
    -0.62
    POSITIVE LOGITS
     respondents
    0.94
     Volunte
    0.86
     surveyed
    0.83
    eva
    0.77
    IU
    0.76
     volunteered
    0.75
     Females
    0.74
    agree
    0.74
     polled
    0.73
     Percent
    0.71
    Activations Density 0.085%

    No Known Activations