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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8931
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or change in location

    oai_token-act-pair · gpt-3.5-turbo

    the start and end tokens of a text document

    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
     stal
    -0.50
     deleg
    -0.49
     cou
    -0.47
     surrounding
    -0.47
     Naz
    -0.45
     Palestin
    -0.45
     Western
    -0.44
     Al
    -0.44
     encomp
    -0.43
     ÂŃ
    -0.43
    POSITIVE LOGITS
    lishes
    0.64
    malink
    0.63
    osponsors
    0.60
    */(
    0.60
     guiActiveUnfocused
    0.60
     ][
    0.60
    redients
    0.60
    tics
    0.59
    cro
    0.58
    llular
    0.57
    Activations Density 0.116%

    No Known Activations