© 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. 11-RES-JB
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations with fictional elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant challenges or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     IA
    -0.46
     Stupid
    -0.44
     PW
    -0.42
     facebook
    -0.41
     VID
    -0.40
    ouver
    -0.40
     ie
    -0.40
     INTO
    -0.40
     AFTER
    -0.39
     thru
    -0.39
    POSITIVE LOGITS
    alions
    0.50
     sqor
    0.49
    UTERS
    0.48
    ĪĴ
    0.47
    é¾į
    0.43
    liest
    0.43
    assad
    0.43
     apiece
    0.42
    stretched
    0.42
    CLUD
    0.42
    Activations Density 1.642%

    No Known Activations