© 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. 4104
    Prev
    Next
    INDEX
    Explanations

    words related to tourist attractions or points of interest

    oai_token-act-pair · gpt-3.5-turbo

    references to various tourist attractions

    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
    м
    -0.80
    plets
    -0.71
     antioxid
    -0.69
    yer
    -0.69
    ounced
    -0.68
    agher
    -0.68
    nikov
    -0.66
    ordan
    -0.65
    Ñı
    -0.65
     PRESIDENT
    -0.64
    POSITIVE LOGITS
     attraction
    1.17
     attractions
    1.15
     Parks
    1.00
    pole
    0.92
    park
    0.92
     park
    0.91
     Resort
    0.90
     parks
    0.88
    Park
    0.88
     Hotel
    0.85
    Activations Density 0.068%

    No Known Activations