© 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. 2046
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and decisions made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and motivations

    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
    arthed
    -0.69
    ¶
    -0.65
    hub
    -0.62
     unison
    -0.60
     Browse
    -0.58
     Ranked
    -0.58
    moil
    -0.57
     §§
    -0.56
    heast
    -0.55
     ballots
    -0.55
    POSITIVE LOGITS
     himself
    1.37
     Himself
    1.08
     remorse
    0.77
    )."
    0.74
     herself
    0.74
     his
    0.72
     subordinates
    0.69
     repentance
    0.67
     buddies
    0.65
     behavi
    0.63
    Activations Density 1.032%

    No Known Activations