© 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. 9-RES-JB
    11. 2485
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and statistical data

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.54
     AND
    -0.51
     or
    -0.45
     firsthand
    -0.45
    abiding
    -0.44
     inexpl
    -0.43
    gyn
    -0.43
    animate
    -0.43
     religiously
    -0.42
    abet
    -0.42
    POSITIVE LOGITS
    inctions
    0.53
    ofi
    0.45
    -+-+
    0.44
    appings
    0.43
    Section
    0.43
    :{
    0.43
    Ĥª
    0.41
     âĵĺ
    0.41
    such
    0.41
     Regions
    0.40
    Activations Density 1.684%

    No Known Activations