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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 3244
    Prev
    Next
    INDEX
    Explanations

    phrases related to political statements regarding Hamas from Israel

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol representation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scattering
    -0.85
    anwhile
    -0.74
     bluff
    -0.68
     dangling
    -0.68
     lodging
    -0.67
    eln
    -0.66
     mate
    -0.64
     coasts
    -0.64
     muse
    -0.63
     devise
    -0.63
    POSITIVE LOGITS
    º
    1.07
    £
    1.01
    ¹
    1.00
    Į
    0.90
    Ķ
    0.88
    ¸
    0.87
    °
    0.86
    ı
    0.86
    į
    0.85
    Ĵ
    0.85
    Activations Density 0.209%

    No Known Activations