© 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. 20889
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing someone's character or abilities

    oai_token-act-pair · gpt-3.5-turbo

    words expressing praise and criticism about people's abilities or qualities

    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
    idav
    -0.73
    ulton
    -0.68
    ARB
    -0.68
     extensive
    -0.65
    armac
    -0.63
    cific
    -0.63
    risome
    -0.62
     feasibility
    -0.61
     elaborate
    -0.60
    yrinth
    -0.60
    POSITIVE LOGITS
    enough
    1.05
     enough
    0.88
     Enough
    0.80
    friends
    0.76
     negotiator
    0.76
     sleeper
    0.75
     undermin
    0.72
    blooded
    0.72
    looking
    0.71
    eyes
    0.71
    Activations Density 0.287%

    No Known Activations