© 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. 13477
    Prev
    Next
    INDEX
    Explanations

    personal names with strong emotional connotations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, organizations, and locations

    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
    »Ĵ
    -0.72
    å¦
    -0.70
    actionDate
    -0.66
    Sem
    -0.65
    tml
    -0.63
    itutes
    -0.63
    rolog
    -0.61
    hematic
    -0.60
    izoph
    -0.59
    achine
    -0.57
    POSITIVE LOGITS
     discovering
    1.24
     agreeing
    1.22
    's
    1.17
     abandoning
    1.15
     adopting
    1.12
     having
    1.11
     refusing
    1.11
     finding
    1.09
     becoming
    1.08
     joining
    1.08
    Activations Density 0.710%

    No Known Activations