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. 22544
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    government-related actions and allocations

    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
    die
    -0.69
    Cong
    -0.66
    onge
    -0.65
    thren
    -0.64
     viz
    -0.63
    arenthood
    -0.62
    Imagine
    -0.61
    Pic
    -0.60
     ancest
    -0.60
    affected
    -0.58
    POSITIVE LOGITS
    arantine
    0.83
     licensing
    0.74
     grants
    0.72
     its
    0.68
     guidelines
    0.68
    atorium
    0.68
     probation
    0.68
     reimburse
    0.67
     subsidies
    0.67
     embassies
    0.67
    Activations Density 0.475%

    No Known Activations