© 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. 0-RES-JB
    11. 1268
    Prev
    Next
    INDEX
    Explanations

    phrases related to buildings or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific buildings

    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
     eye
    -0.65
     throat
    -0.65
     ple
    -0.64
     serv
    -0.63
     subp
    -0.63
     rem
    -0.63
     flick
    -0.63
     aven
    -0.63
    jad
    -0.62
     contr
    -0.62
    POSITIVE LOGITS
     Building
    3.78
    Building
    2.65
     Buildings
    2.19
     building
    1.93
    building
    1.75
     Build
    1.57
    Build
    1.46
     Built
    1.35
     Architects
    1.33
     Construction
    1.31
    Activations Density 0.010%

    No Known Activations