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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15075
    Prev
    Next
    INDEX
    Explanations

    scientific publication references in the format of dois and URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to images or visuals associated with articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disadvant
    -0.48
     destro
    -0.45
    sic
    -0.45
    enegger
    -0.43
     helicop
    -0.43
    avorite
    -0.42
    Interstitial
    -0.42
     [*
    -0.42
     nomine
    -0.41
     behav
    -0.39
    POSITIVE LOGITS
    º
    0.44
     âĢº
    0.40
    ®
    0.38
     Corbyn
    0.37
    zbollah
    0.36
    alyses
    0.35
    ĭ
    0.35
     Abbas
    0.35
     ):
    0.35
    ļ
    0.34
    Activations Density 2.588%

    No Known Activations