© 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. 10-RES-JB
    11. 8574
    Prev
    Next
    INDEX
    Explanations

    the prefix "ne" followed by a single character or multiple characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the segment "ne" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENSE
    -0.67
    Ranked
    -0.65
    hips
    -0.59
     locker
    -0.58
     recalling
    -0.57
     lockout
    -0.57
    IENT
    -0.57
     hotels
    -0.55
     ecstasy
    -0.55
     pains
    -0.55
    POSITIVE LOGITS
    braska
    1.17
    uter
    1.13
    olithic
    1.13
    ccess
    1.11
    arthed
    1.08
    farious
    1.07
    verend
    1.05
    cro
    1.01
    arest
    0.98
    uters
    0.93
    Activations Density 0.021%

    No Known Activations