© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8790
    Prev
    Next
    INDEX
    Explanations

    mentions of specific mobile phone processors, particularly Snapdragon series by Qualcomm

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific Snapdragon processors and Qualcomm-related terminology

    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
    gotten
    -0.86
    capt
    -0.71
    swick
    -0.71
    agall
    -0.70
    sted
    -0.69
    stad
    -0.67
     Bucs
    -0.67
    vernment
    -0.67
    conserv
    -0.67
     Cosponsors
    -0.67
    POSITIVE LOGITS
     Snapdragon
    1.41
     chipset
    0.93
     coils
    0.85
    Intel
    0.82
     processors
    0.81
     alloy
    0.81
     Qualcomm
    0.81
     chips
    0.78
    Chip
    0.76
     coil
    0.73
    Activations Density 0.011%

    No Known Activations