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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 3244
    Prev
    Next
    INDEX
    Explanations

    sentences where a general word or concept is described in specific detail

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by various other terms or adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Edit
    -0.86
    istar
    -0.77
    enery
    -0.73
    coins
    -0.73
    andon
    -0.72
    IPS
    -0.70
    Versions
    -0.70
    otte
    -0.69
    uin
    -0.69
    blocks
    -0.69
    POSITIVE LOGITS
     cornerstone
    1.13
     manifestation
    1.04
     reflection
    1.01
     symptom
    1.01
     subset
    1.00
     lot
    0.99
     metaphor
    0.98
     hallmark
    0.98
     distraction
    0.97
     prerequisite
    0.97
    Activations Density 0.245%

    No Known Activations