© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 10000
    Prev
    Next
    INDEX
    Explanations

    future tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    conditional or future-oriented statements often emphasizing potential outcomes or possibilities

    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
     Conference
    -0.67
     Crom
    -0.63
     citing
    -0.62
     Quart
    -0.59
    ials
    -0.59
     Mell
    -0.59
     Cec
    -0.58
    âĺ
    -0.58
    ions
    -0.58
     supper
    -0.58
    POSITIVE LOGITS
     culmin
    0.88
     underpin
    0.83
     propel
    0.83
     expose
    0.82
     characterize
    0.80
    ¶ħ
    0.80
     accompany
    0.78
     allow
    0.78
    é¾įå¥ij士
    0.77
     someday
    0.76
    Activations Density 0.174%

    No Known Activations