Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15847
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with 'to' followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases about desires or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.83
    ÃĥÃĤÃĥÃĤ
    -0.69
    interstitial
    -0.68
    accompanied
    -0.68
     Kinnikuman
    -0.67
    imore
    -0.67
    reports
    -0.66
    rising
    -0.66
    soDeliveryDate
    -0.65
    written
    -0.65
    POSITIVE LOGITS
     maximize
    1.22
     conserve
    1.17
     pursue
    1.13
     emulate
    1.13
     indulge
    1.11
     avoid
    1.11
     delve
    1.11
     broaden
    1.07
     recreate
    1.07
     succeed
    1.05
    Activations Density 0.078%

    No Known Activations