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. 9821
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate struggle or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    instances of struggle or difficulty in achieving various goals

    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
    Fax
    -0.83
    usra
    -0.81
    çīĪ
    -0.77
    prints
    -0.72
     Tribune
    -0.72
    azon
    -0.70
     Torch
    -0.68
    YES
    -0.68
    soType
    -0.66
     Sign
    -0.66
    POSITIVE LOGITS
     cope
    0.93
     recovering
    0.89
     grasp
    0.86
     reconcile
    0.84
     regain
    0.79
     recover
    0.79
     rebound
    0.79
     conceive
    0.79
     fend
    0.77
     reproduce
    0.76
    Activations Density 0.175%

    No Known Activations