INDEX

Explanations

terms related to strength or intensity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.75

 betweenstory

-0.71

 مرئيه

-0.69

yntaxException

-0.66

djangoproject

-0.65

bleven

-0.63

MLLoader

-0.61

 leſs

-0.61

DockStyle

-0.60

ništ

-0.60

POSITIVE LOGITS

 willed

0.84

STRONG

0.82

 Weak

0.80

strong

0.76

 weak

0.74

weak

0.73

Strong

0.72

 Strong

0.72

+#+

0.71

 💪

0.70

Activations Density 0.152%

terms related to strength or intensity

No Comments

No Known Activations