© 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. 9-RES-JB
    11. 8997
    Prev
    Next
    INDEX
    Explanations

    references to mountainous landscapes and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic features, particularly mountains and hills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emails
    -0.81
     copies
    -0.72
    Os
    -0.65
     Boeing
    -0.65
     DOD
    -0.63
     Sponsor
    -0.61
     copy
    -0.61
     faulty
    -0.59
     Moves
    -0.59
     Orche
    -0.59
    POSITIVE LOGITS
     overlooking
    1.12
     slope
    1.12
     cliffs
    1.11
     valley
    1.07
     slopes
    1.07
     canyon
    1.02
     hills
    1.01
     valleys
    1.01
     separating
    1.00
     gorge
    0.99
    Activations Density 0.241%

    No Known Activations