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. 12-RES-JB
    6. 15248
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech with past tense verbs indicating experiences or conversations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that indicate past experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĺħ
    -0.85
    ModLoader
    -0.81
    KER
    -0.77
    rawdownloadcloneembedreportprint
    -0.76
    CLASSIFIED
    -0.75
    CTV
    -0.75
    Reviewer
    -0.73
    Textures
    -0.71
    OTOS
    -0.71
    DAQ
    -0.71
    POSITIVE LOGITS
     been
    1.18
     gotten
    1.16
     forgotten
    1.10
     eaten
    1.03
     seen
    1.00
     grown
    0.98
     flown
    0.98
     gone
    0.97
     done
    0.96
     begun
    0.95
    Activations Density 0.071%

    No Known Activations