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. 10-RES-JB
    6. 18398
    Prev
    Next
    INDEX
    Explanations

    phrases related to outdoor social gatherings or physical structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tail" and its variations, often in a context related to animals or metaphorical uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.67
    oulos
    -0.62
    éĹĺ
    -0.61
    psons
    -0.61
    Constructed
    -0.61
     Hindi
    -0.61
     Brotherhood
    -0.60
    iscopal
    -0.60
     conversions
    -0.59
     CES
    -0.59
    POSITIVE LOGITS
    bone
    1.34
    piece
    1.07
    oring
    1.05
    wind
    1.02
    fin
    1.01
     fins
    0.98
     feathers
    0.98
    pipe
    0.97
    bones
    0.97
    pieces
    0.95
    Activations Density 0.025%

    No Known Activations