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. 1-RES-JB
    6. 17901
    Prev
    Next
    INDEX
    Explanations

    keywords related to charging or recharging devices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to battery charging and technological devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.77
     Pieces
    -0.69
     pse
    -0.67
    ç¥ŀ
    -0.66
    pei
    -0.65
    ³
    -0.62
    åı
    -0.62
    º
    -0.61
    76561
    -0.60
     losers
    -0.60
    POSITIVE LOGITS
    Charge
    1.22
    charge
    1.16
    charges
    1.10
    charged
    1.03
    charging
    0.96
    charg
    0.95
    agher
    0.90
    assador
    0.84
     recharge
    0.84
    cation
    0.79
    Activations Density 0.018%

    No Known Activations