© 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. 23887
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Chromecast" in different contexts or technical details

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Chrom" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Lisbon
    -0.72
     caution
    -0.71
    ulton
    -0.68
    REDACTED
    -0.66
    riors
    -0.65
     plur
    -0.64
    inen
    -0.63
    FORMATION
    -0.63
    WARD
    -0.61
     productivity
    -0.59
    POSITIVE LOGITS
    ecast
    1.32
    atic
    1.10
    atin
    0.98
    atics
    0.95
    atically
    0.94
    odynamics
    0.93
    elight
    0.93
    edy
    0.93
    atography
    0.92
    andise
    0.91
    Activations Density 0.047%

    No Known Activations