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. 14236
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction or conflict

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "of" in various contexts

    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
    ucci
    -0.56
     reperto
    -0.53
     destro
    -0.53
    acus
    -0.50
    wagon
    -0.50
     challeng
    -0.49
     caut
    -0.49
     describ
    -0.48
    wcs
    -0.48
     rul
    -0.47
    POSITIVE LOGITS
     JUSTICE
    0.48
     sorts
    0.48
     course
    0.48
    icial
    0.42
     Science
    0.41
     Gear
    0.40
     doom
    0.40
     Darkness
    0.40
     Investigation
    0.40
     RELE
    0.40
    Activations Density 0.453%

    No Known Activations