© 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. 3-RES-JB
    11. 3406
    Prev
    Next
    INDEX
    Explanations

    terms related to examinations or trials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tests and experimental evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Narr
    -0.59
    shield
    -0.57
    BN
    -0.54
    ress
    -0.54
    Hur
    -0.54
    entity
    -0.54
     Nost
    -0.54
    scape
    -0.53
     gentleman
    -0.53
    nia
    -0.53
    POSITIVE LOGITS
    hops
    1.41
    poons
    1.39
    ettings
    1.35
    uggest
    1.34
    mith
    1.30
    hips
    1.29
    paces
    1.26
    afety
    1.24
    ynthesis
    1.21
    pring
    1.21
    Activations Density 0.147%

    No Known Activations