© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 11751
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, such as cities and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and entities, particularly in relation to sports and geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )."
    -0.76
    ]."
    -0.74
    ).[
    -0.63
     meanwhile
    -0.61
    .'"
    -0.61
    .")
    -0.61
    '."
    -0.61
    )].
    -0.58
    ĵĺ
    -0.57
    anwhile
    -0.55
    POSITIVE LOGITS
    uin
    0.50
     GU
    0.44
     ancestor
    0.43
    owship
    0.43
     ITS
    0.42
     Heavenly
    0.42
     i
    0.41
    Firstly
    0.41
     AX
    0.41
     ORIG
    0.41
    Activations Density 3.399%

    No Known Activations