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. 7-RES-JB
    6. 440
    Prev
    Next
    INDEX
    Explanations

    references to physical locations like rooms or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to physical spaces and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vengeance
    -0.80
     ransom
    -0.72
     nerve
    -0.71
     blackmail
    -0.66
     serial
    -0.66
     fireball
    -0.63
     bastard
    -0.63
    awar
    -0.62
     indictment
    -0.62
    ãĥ©ãĥ³
    -0.61
    POSITIVE LOGITS
     amenities
    1.03
     seating
    0.97
    paces
    0.96
     spaces
    0.93
    cape
    0.88
     Spaces
    0.88
     accommodations
    0.86
     adjoining
    0.83
    hips
    0.83
    pace
    0.81
    Activations Density 0.196%

    No Known Activations