© 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. 3115
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning or anticipation

    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
    ?".
    -0.62
    âĢ¦"
    -0.60
    âĢ¦."
    -0.59
    """
    -0.59
     unison
    -0.58
    ]"
    -0.56
    ADVERTISEMENT
    -0.56
    ãĢį
    -0.56
    }"
    -0.56
    selves
    -0.56
    POSITIVE LOGITS
     himself
    0.87
     herself
    0.69
     cameo
    0.66
     solo
    0.64
     autobi
    0.61
     charisma
    0.61
    veland
    0.60
     autobiography
    0.59
    udos
    0.59
     honorary
    0.58
    Activations Density 1.126%

    No Known Activations