© 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. 9-RES-JB
    11. 9962
    Prev
    Next
    INDEX
    Explanations

    exact details or specifics within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "exactly" and its variations, indicating precise information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULTS
    -0.71
    BSD
    -0.70
    MRI
    -0.64
    ework
    -0.64
    roe
    -0.63
    very
    -0.61
     moderately
    -0.61
     Tome
    -0.61
     immensely
    -0.60
    IRO
    -0.60
    POSITIVE LOGITS
     how
    0.85
     HOW
    0.84
    why
    0.83
     WHY
    0.81
     why
    0.79
    omething
    0.79
    what
    0.76
     whats
    0.74
     transpired
    0.71
    ifications
    0.70
    Activations Density 0.031%

    No Known Activations