Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 6581
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculation about potential scenarios

    oai_token-act-pair · gpt-3.5-turbo

    speculations and hypotheticals about future or past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fort
    -0.67
    onz
    -0.65
    claimer
    -0.62
    iard
    -0.62
    izen
    -0.62
    ience
    -0.59
     quoting
    -0.58
     citing
    -0.58
    quartered
    -0.57
    lication
    -0.57
    POSITIVE LOGITS
     happen
    1.33
     transpired
    1.32
     happened
    1.24
     happens
    1.10
     Happ
    1.03
     happ
    1.03
     motivate
    1.00
     occur
    0.93
     ensued
    0.90
     motiv
    0.88
    Activations Density 0.092%

    No Known Activations