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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17296
    Prev
    Next
    INDEX
    Explanations

    phrases related to sanctimonious behavior

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific syllables or sounds in various words

    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
    bang
    -0.65
    atche
    -0.65
     Norn
    -0.63
    tags
    -0.61
    rew
    -0.60
    better
    -0.59
    earable
    -0.57
    FUL
    -0.56
    patrick
    -0.55
     Paste
    -0.55
    POSITIVE LOGITS
    ials
    1.19
    ious
    1.18
    ial
    1.16
    strous
    1.05
    etary
    1.03
    itored
    1.03
    iously
    1.02
    ium
    0.97
    iac
    0.96
    uclear
    0.93
    Activations Density 0.054%

    No Known Activations