INDEX

Explanations

a structure or pattern related to computer programming or technical formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.86

出版年

-0.83

URLException

-0.76

NUMX

-0.74

Lähde

-0.73

 <>",

-0.72

tagHelperRunner

-0.72

+#+

-0.72

 Houſe

-0.71

amaño

-0.71

POSITIVE LOGITS

<eos>

0.97

<bos>

0.88

↵↵

0.82

↵

0.71

↵↵↵

0.61

))

0.57

↵↵↵↵

0.56

}}

0.55

。

0.53

↵↵↵↵↵

0.53

Activations Density 0.544%

a structure or pattern related to computer programming or technical formats

No Comments

No Known Activations