© 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. 23473
    Prev
    Next
    INDEX
    Explanations

    phrases related to either personal opinions or unresolved issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "haven't" and its variations, often implying a sense of absence or lack

    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
    Subject
    -0.68
     prone
    -0.65
     complicit
    -0.64
     Subject
    -0.61
    OTAL
    -0.61
     subject
    -0.60
    GROUP
    -0.59
    åħī
    -0.59
    UE
    -0.59
    Pierre
    -0.59
    POSITIVE LOGITS
    been
    1.06
     been
    0.83
     Been
    0.72
    yet
    0.69
     gotten
    0.69
    ¥ŀ
    0.66
    ailability
    0.66
    gotten
    0.66
    udence
    0.65
    gged
    0.64
    Activations Density 0.062%

    No Known Activations