© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6400
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    oai_token-act-pair · gpt-3.5-turbo

    elements related to categories of news or information

    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
     distribution
    -0.50
     establishment
    -0.50
     salute
    -0.48
     PCB
    -0.48
     DPS
    -0.48
     integrity
    -0.47
     uncond
    -0.46
     AT
    -0.45
     Coulter
    -0.45
     conversion
    -0.45
    POSITIVE LOGITS
    weeney
    0.77
    igslist
    0.75
    ictionary
    0.72
    ocre
    0.70
    ļéĨĴ
    0.66
    ibal
    0.65
    onyms
    0.64
     pione
    0.64
    retty
    0.64
    ü
    0.64
    Activations Density 1.670%

    No Known Activations