© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 4073
    Prev
    Next
    INDEX
    Explanations

    words related to the side of an object or area

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations or settings

    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
    anson
    -1.11
    strings
    -0.96
    eming
    -0.93
    ional
    -0.93
    alf
    -0.91
    aido
    -0.91
    uga
    -0.90
    orius
    -0.89
    iments
    -0.87
    oras
    -0.86
    POSITIVE LOGITS
     attractions
    0.85
     café
    0.85
     attraction
    0.82
     snack
    0.80
     cafe
    0.80
     cafes
    0.77
     diner
    0.76
     Savior
    0.76
     hospitality
    0.75
     restaurant
    0.75
    Activations Density 0.153%

    No Known Activations