© 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
    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. 3109
    Prev
    Next
    INDEX
    Explanations

    specific locations mentioned in a news or crime-related text

    oai_token-act-pair · gpt-3.5-turbo
    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
     reperto
    -0.85
     oblig
    -0.77
     submar
    -0.74
     discipl
    -0.72
    orian
    -0.72
     repertoire
    -0.72
     ignor
    -0.66
     indisp
    -0.64
     pron
    -0.63
    />
    -0.63
    POSITIVE LOGITS
     flats
    0.94
     Interstate
    0.92
     Northeast
    0.80
     Boulevard
    0.79
     Sunset
    0.78
     stairs
    0.78
     Northwest
    0.77
     Rue
    0.77
     Commissioners
    0.75
     Avenue
    0.75
    Activations Density 0.066%

    No Known Activations