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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    6. 2411
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations, particularly harbors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organisation
    -0.73
     organisations
    -0.73
     analyse
    -0.72
     pupils
    -0.72
    ess
    -0.72
     programme
    -0.68
     emphas
    -0.67
     favourite
    -0.66
     Isis
    -0.65
     favourites
    -0.65
    POSITIVE LOGITS
     Harbor
    4.59
     Harbour
    2.32
     harbor
    2.04
     harbour
    1.32
     Cove
    1.24
     Shore
    1.14
     docks
    1.07
     Beach
    1.06
     waterfront
    1.06
     Seas
    1.01
    Activations Density 0.011%

    No Known Activations