© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13950
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects or impacts of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to effects or implications of actions or policies

    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
    §
    -0.69
    Ancient
    -0.64
    achus
    -0.63
    £ı
    -0.62
     Ded
    -0.61
    eon
    -0.61
    ctuary
    -0.61
    stretched
    -0.61
    acus
    -0.61
     manually
    -0.59
    POSITIVE LOGITS
     impact
    1.56
     effect
    1.53
     effects
    1.44
     impacts
    1.42
    effect
    1.34
     consequences
    1.33
    effects
    1.32
     repercussions
    1.32
     effectiveness
    1.30
    impact
    1.29
    Activations Density 0.729%

    No Known Activations