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. 2663
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names present in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names

    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
     iP
    -0.86
     weap
    -0.85
     misunder
    -0.82
     behav
    -0.73
     polic
    -0.73
     trump
    -0.72
     disapp
    -0.72
     econom
    -0.72
     streng
    -0.70
     acknow
    -0.69
    POSITIVE LOGITS
    utenberg
    1.10
    atha
    1.06
    ida
    1.06
    atum
    1.05
    ata
    1.04
    enei
    1.02
    ila
    1.01
    ĸļ士
    1.00
    aga
    1.00
    onica
    0.99
    Activations Density 0.334%

    No Known Activations