© 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. 7-RES-JB
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and memories

    oai_token-act-pair · gpt-3.5-turbo

    narratives about personal experiences in an educational context

    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
     Hezbollah
    -0.68
     "'
    -0.68
    xit
    -0.64
    Elsewhere
    -0.63
     2024
    -0.61
     Caption
    -0.60
     ISIL
    -0.59
     enshr
    -0.59
     Goodell
    -0.58
     Islamists
    -0.58
    POSITIVE LOGITS
     myself
    1.08
     my
    1.02
     haha
    0.89
     alot
    0.84
     ðŁĻĤ
    0.79
     blogging
    0.79
     :)
    0.77
    Âł
    0.75
    My
    0.72
     :(
    0.71
    Activations Density 1.744%

    No Known Activations