Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21888
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions indicating increasing intensity or frequency

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "more" in various contexts

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

    No Comments

    Negative Logits
    xtap
    -0.76
    pex
    -0.68
     2024
    -0.67
     Released
    -0.64
    oresc
    -0.63
    OCK
    -0.63
     Classification
    -0.61
    adium
    -0.61
     Nord
    -0.59
    gee
    -0.59
    POSITIVE LOGITS
     than
    1.33
    than
    0.90
     importantly
    0.89
     ado
    0.88
     stringent
    0.87
     elaborate
    0.85
     manageable
    0.84
     sophisticated
    0.84
     Than
    0.81
     efficient
    0.81
    Activations Density 0.169%

    No Known Activations