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. 3-RES-JB
    6. 14195
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     digestion
    -0.74
    peat
    -0.70
     bandwagon
    -0.68
    meat
    -0.64
     machines
    -0.62
     licenses
    -0.62
     expansions
    -0.61
     hiber
    -0.60
    ktop
    -0.60
    hare
    -0.59
    POSITIVE LOGITS
    oshop
    0.84
    uran
    0.74
    ndra
    0.74
    izophren
    0.69
    ̶
    0.69
    erman
    0.68
     :=
    0.68
    oman
    0.67
    auder
    0.67
    isconsin
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.