© 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. 7-RES-JB
    11. 22997
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions, consequences, and effects

    oai_token-act-pair · gpt-3.5-turbo

    key actions or significant events that influence outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _>
    -0.82
     consulted
    -0.67
    yd
    -0.65
    cision
    -0.64
     retained
    -0.63
     supervised
    -0.63
     overseen
    -0.62
     wielding
    -0.60
     unaccompanied
    -0.60
     Referred
    -0.59
    POSITIVE LOGITS
     nerves
    0.85
     morale
    0.79
     viewers
    0.78
     me
    0.76
     us
    0.73
     reverber
    0.71
    notations
    0.69
     resonate
    0.65
     audiences
    0.65
    eur
    0.64
    Activations Density 0.405%

    No Known Activations