© 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. 6-RES-JB
    11. 2884
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to legal issues or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Secondly
    -0.57
    Optional
    -0.55
     targ
    -0.53
     (=
    -0.52
    interpret
    -0.52
     Afterwards
    -0.51
    arrow
    -0.51
    Normal
    -0.50
    Therefore
    -0.50
    aration
    -0.50
    POSITIVE LOGITS
     POLITICO
    0.65
     NASCAR
    0.63
    LOS
    0.58
     headlines
    0.57
     embattled
    0.57
     skeptics
    0.56
     Phillies
    0.56
     Philly
    0.56
     HuffPost
    0.54
     shockingly
    0.54
    Activations Density 1.243%

    No Known Activations