© 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. 2-RES-JB
    11. 10460
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names starting with 'Kirst' and variations of the word 'First'

    oai_token-act-pair · gpt-3.5-turbo

    instances of names or proper nouns, particularly those related to individuals or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Logged
    -0.76
     newsletters
    -0.63
     Holo
    -0.62
    posium
    -0.62
    ptions
    -0.61
     Acad
    -0.60
     citation
    -0.59
    Putin
    -0.57
     Recomm
    -0.56
    Apr
    -0.56
    POSITIVE LOGITS
    yles
    0.99
    rikes
    0.95
    irst
    0.92
    rike
    0.88
    yle
    0.87
    say
    0.87
    ory
    0.82
    upid
    0.82
    yne
    0.81
    obal
    0.80
    Activations Density 0.012%

    No Known Activations