© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and certain notable entities

    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
    theless
    -0.63
    ODUCT
    -0.61
    éĹ
    -0.59
    Pg
    -0.58
    iversary
    -0.58
    tenance
    -0.54
     reckoned
    -0.53
    ãĤ¨ãĥ«
    -0.51
    æĢ
    -0.51
    âĶĢâĶĢ
    -0.50
    POSITIVE LOGITS
    utsch
    0.68
    nih
    0.65
    ode
    0.60
    oub
    0.60
    asse
    0.56
    ata
    0.55
    esi
    0.55
    omm
    0.54
    ymes
    0.54
    si
    0.54
    Activations Density 0.844%

    No Known Activations