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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 593
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription offers and call-to-action messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nikov
    -0.72
    gn
    -0.70
    ynt
    -0.70
    ynthesis
    -0.68
    akov
    -0.68
    geist
    -0.68
     Pwr
    -0.66
    matter
    -0.66
    edi
    -0.66
     hardness
    -0.66
    POSITIVE LOGITS
    OSE
    0.71
    zens
    0.70
    Subscribe
    0.67
     strives
    0.66
    à¤
    0.66
     Hover
    0.65
    pictured
    0.64
    iframe
    0.63
    èĪ
    0.63
    Heart
    0.63
    Activations Density 0.086%

    No Known Activations