© 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. 8-RES-JB
    11. 9468
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "H" in various contexts

    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
    enhagen
    -0.76
     instr
    -0.69
     scales
    -0.69
     sheet
    -0.67
    chers
    -0.65
     reversible
    -0.64
    gradient
    -0.64
     flush
    -0.63
    ãĤ´ãĥ³
    -0.63
     thumbs
    -0.63
    POSITIVE LOGITS
    ospital
    1.30
    arrison
    1.21
    IGH
    1.21
    ISTORY
    1.21
    anging
    1.20
    ollywood
    1.18
    umble
    1.15
    annah
    1.15
    ometown
    1.14
    alloween
    1.14
    Activations Density 0.048%

    No Known Activations