INDEX

Explanations

code snippets related to programming errors or debugging issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

albeit

-0.95

 whatnot

-0.93

 saurait

-0.93

 albeit

-0.88

 tantôt

-0.87

 hitherto

-0.85

 MainAxisSize

-0.84

 hence

-0.83

Rüyada

-0.83

 lenker

-0.82

POSITIVE LOGITS

 begin

0.71

don

0.60

 create

0.51

 began

0.51

 must

0.50

tificate

0.50

 maybe

0.50

 every

0.50

 Because

0.49

 result

0.49

Activations Density 0.657%

code snippets related to programming errors or debugging issues

No Comments

No Known Activations