© 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. 0-RES-JB
    11. 6501
    Prev
    Next
    INDEX
    Explanations

    words related to the month of September or prefixes/suffixes of the word "September"

    oai_token-act-pair · gpt-3.5-turbo

    the word "ember" and its variations, indicating a focus on the concept of "ember" or related terms

    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
     lo
    -0.66
     strains
    -0.65
     stall
    -0.63
     yes
    -0.63
     Sid
    -0.62
     favored
    -0.61
     circling
    -0.61
     senators
    -0.61
     suggestive
    -0.60
     Senators
    -0.59
    POSITIVE LOGITS
    ember
    5.09
    EMBER
    2.05
    ober
    1.40
    mber
    1.39
     Ember
    1.29
    cember
    1.15
    uary
    1.09
    nesday
    1.01
    ecycle
    1.00
    ufact
    1.00
    Activations Density 0.014%

    No Known Activations