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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 2664
    Prev
    Next
    INDEX
    Explanations

    mentions of things happening recently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lately" and related temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.89
    tein
    -0.87
    eer
    -0.83
    oat
    -0.80
    amina
    -0.80
    gravity
    -0.74
    claimer
    -0.74
    iop
    -0.71
    ologies
    -0.71
    aughtered
    -0.71
    POSITIVE LOGITS
     lately
    1.07
     inactive
    0.85
     overlooked
    0.84
     slump
    0.79
     unsus
    0.78
     overshadowed
    0.75
     forgotten
    0.74
     discont
    0.72
     asleep
    0.72
     spate
    0.72
    Activations Density 0.003%

    No Known Activations