© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    words related to making decisions or reaching conclusions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "resolution" and its variations

    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
     bunk
    -0.71
    riger
    -0.68
    apult
    -0.66
    ula
    -0.65
     Pants
    -0.64
    opathic
    -0.63
    mith
    -0.63
     Boo
    -0.60
    uka
    -0.60
    duct
    -0.60
    POSITIVE LOGITS
     resolution
    4.08
     resolutions
    3.09
     Resolution
    3.05
    resolution
    2.63
     resolving
    1.88
     resolved
    1.68
     resolve
    1.68
     resolves
    1.67
     clarity
    1.16
     fidelity
    1.16
    Activations Density 0.020%

    No Known Activations