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. 11-RES-JB
    6. 9807
    Prev
    Next
    INDEX
    Explanations

    mentions of personal attributes or actions related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their statements or issues related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.94
     GOODMAN
    -0.76
    yang
    -0.71
    intendent
    -0.71
     NAD
    -0.69
    uders
    -0.69
    ghai
    -0.69
    ato
    -0.69
    amaz
    -0.68
     Mages
    -0.68
    POSITIVE LOGITS
     qualifications
    1.22
     temperament
    1.22
     stances
    1.21
     candidacy
    1.17
     speeches
    1.16
     presidency
    1.14
     upbringing
    1.05
     patriotism
    1.05
     stamina
    1.04
     charisma
    1.00
    Activations Density 0.394%

    No Known Activations