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

    Neuronpedia

    Jacobian LensNEW
    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. 21115
    Prev
    Next
    INDEX
    Explanations

    instances of sentences starting with 'it is' or 'it's', indicating evaluations or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    structures indicating hypothetical or conditional 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
    ĸļ
    -0.72
    Priv
    -0.67
     Management
    -0.65
    Ore
    -0.64
     Ratio
    -0.64
     Syndrome
    -0.62
    ++++
    -0.62
    imon
    -0.60
    assembly
    -0.59
    ulner
    -0.59
    POSITIVE LOGITS
    veland
    0.80
     consciously
    0.77
     passively
    0.68
     guessed
    0.67
     includ
    0.67
     chooses
    0.67
     preached
    0.66
     perceive
    0.65
     coasts
    0.65
     livest
    0.64
    Activations Density 0.079%

    No Known Activations