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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 19383
    Prev
    Next
    INDEX
    Explanations

    words that contain the sequence "fe"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "fe" in various contexts, possibly indicating a focus on the concept of "feeling" or related sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worthy
    -0.70
     GEAR
    -0.65
    antically
    -0.61
    70710
    -0.60
     Colleges
    -0.59
    stretched
    -0.58
    nas
    -0.58
    stood
    -0.58
     Visitors
    -0.58
     ANGEL
    -0.58
    POSITIVE LOGITS
    eling
    1.06
    cker
    1.00
    encing
    0.96
    ppings
    0.96
    ck
    0.94
    ffer
    0.93
    els
    0.93
    ences
    0.92
    ying
    0.92
    xt
    0.92
    Activations Density 0.004%

    No Known Activations