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. 11370
    Prev
    Next
    INDEX
    Explanations

    descriptions related to events or happenings, showcasing a mix of different activities and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    elements conveying sensory experiences related to scent and atmosphere

    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
     mediation
    -0.64
     arbitration
    -0.63
     relying
    -0.61
    intelligence
    -0.61
     coerc
    -0.60
     discredited
    -0.59
     coercion
    -0.59
     unilaterally
    -0.58
     ineffective
    -0.58
     constitution
    -0.58
    POSITIVE LOGITS
     celebrate
    0.73
     Guinness
    0.71
    gallery
    0.71
     homage
    0.69
    Kids
    0.66
     gorgeous
    0.66
     themed
    0.65
     rave
    0.64
     Celebration
    0.63
    Cele
    0.63
    Activations Density 2.778%

    No Known Activations