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. 10-RES-JB
    6. 30
    Prev
    Next
    INDEX
    Explanations

    phrases related to attribution or significance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violations or significant impacts on rights and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enne
    -0.75
    yd
    -0.64
    enium
    -0.63
    affected
    -0.63
    uve
    -0.62
    fam
    -0.62
    assies
    -0.62
    edo
    -0.60
    engers
    -0.60
    oqu
    -0.59
    POSITIVE LOGITS
     an
    0.98
     a
    0.97
     heresy
    0.93
     something
    0.85
     salvation
    0.85
     betrayal
    0.83
     blasphemy
    0.81
     obstruction
    0.80
     collusion
    0.79
     complicity
    0.79
    Activations Density 0.079%

    No Known Activations