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. 8-RES-JB
    6. 18161
    Prev
    Next
    INDEX
    Explanations

    statistics and comparisons related to different groups or factors

    oai_token-act-pair · gpt-3.5-turbo

    statistics and likelihood comparisons related to various social groups and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.79
     Revelations
    -0.69
     Peb
    -0.68
     nutshell
    -0.64
     suffice
    -0.63
     totality
    -0.63
     Bullets
    -0.62
     lasers
    -0.62
    ufact
    -0.62
    kos
    -0.61
    POSITIVE LOGITS
     disproportionately
    1.03
     likely
    0.96
     poorer
    0.93
     statistically
    0.92
     propensity
    0.91
     prone
    0.83
     socially
    0.83
     cognitive
    0.82
     susceptibility
    0.82
     median
    0.82
    Activations Density 0.457%

    No Known Activations