Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16906
    Prev
    Next
    INDEX
    Explanations

    geographical locations and environmental features

    oai_token-act-pair · gpt-3.5-turbo

    geographical or environmental references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reme
    -0.79
    McC
    -0.71
    HK
    -0.68
    Counter
    -0.67
    NSA
    -0.67
    RON
    -0.66
    Roy
    -0.66
    OTOS
    -0.66
    ISTER
    -0.63
    ISA
    -0.63
    POSITIVE LOGITS
     lakes
    0.99
     vegetation
    0.98
     basin
    0.96
     dams
    0.93
     Fisheries
    0.93
     forests
    0.93
     habitat
    0.92
     migr
    0.92
     inland
    0.91
     lake
    0.91
    Activations Density 0.714%

    No Known Activations