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. 8-RES-JB
    6. 9054
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions or requirements for specific actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the importance of value and conditions for achieving goals

    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
    cknow
    -0.77
    tips
    -0.67
     diaper
    -0.67
     enjoyment
    -0.62
    cknowled
    -0.61
    Synopsis
    -0.60
    Phill
    -0.59
     Leilan
    -0.59
    Advertisements
    -0.58
     chatting
    -0.58
    POSITIVE LOGITS
    requires
    1.04
     must
    0.98
     requires
    0.98
    must
    0.97
    apo
    0.85
     required
    0.85
     require
    0.84
    needs
    0.82
     MUST
    0.82
     needs
    0.79
    Activations Density 0.389%

    No Known Activations