© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 21019
    Prev
    Next
    INDEX
    Explanations

    the word "nobody" followed by a situation or attribute

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nobody" suggesting a focus on themes of absence or lack of recognition

    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
    heny
    -0.77
     Nanto
    -0.74
    rick
    -0.71
    Ont
    -0.69
    CBC
    -0.66
    Gaza
    -0.66
     Lank
    -0.66
    eder
    -0.65
     Metatron
    -0.63
    Kin
    -0.62
    POSITIVE LOGITS
     else
    1.25
    soever
    1.05
    zzle
    0.89
    etheless
    0.87
    THING
    0.86
     bothering
    0.83
     hesitate
    0.82
    ĪĴ
    0.78
    xus
    0.76
    IRD
    0.76
    Activations Density 0.008%

    No Known Activations