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. 7-RES-JB
    6. 7661
    Prev
    Next
    INDEX
    Explanations

    phrases related to reaching a conclusion or realization

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "come to," indicating a focus on realizations or conclusions reached by subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hierarch
    -0.74
     Coup
    -0.65
     priceless
    -0.61
    Rocket
    -0.61
    llan
    -0.58
     conveyed
    -0.56
    vich
    -0.56
     Hebdo
    -0.55
     quot
    -0.55
     incoming
    -0.54
    POSITIVE LOGITS
     grips
    1.17
     fruition
    1.07
     blows
    0.98
     prominence
    0.93
     conclusions
    0.85
     realise
    0.82
     haunt
    0.79
     realize
    0.78
     dominate
    0.78
     settle
    0.76
    Activations Density 0.093%

    No Known Activations