© 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. 23464
    Prev
    Next
    INDEX
    Explanations

    mentions of the car brand "Honda"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the car brand Honda and its models

    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
    ablishment
    -0.87
    orial
    -0.82
     Seym
    -0.81
    */(
    -0.80
    byter
    -0.79
    tle
    -0.78
    acular
    -0.78
    utherford
    -0.73
    olves
    -0.72
    asure
    -0.72
    POSITIVE LOGITS
     Civic
    0.93
     Accord
    0.89
     Motor
    0.82
     Odyssey
    0.82
     Rouse
    0.80
     Karin
    0.75
     Prelude
    0.74
     Honda
    0.73
    asaki
    0.73
    ota
    0.71
    Activations Density 0.027%

    No Known Activations