INDEX

Explanations

negations and their accompanying phrases

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

avond

-0.64

+#+#

-0.63

حياتها

-0.57

iastes

-0.52

Demografia

-0.51

 resourceCulture

-0.50

ⓧ

-0.50

DockStyle

-0.49

حياته

-0.47

exitRule

-0.47

POSITIVE LOGITS

 mention

1.07

 Mention

0.87

 mentioning

0.79

mention

0.76

ISupport

0.72

 mentions

0.72

Mention

0.70

 forget

0.69

 forgetting

0.65

 виправивши

0.61

Activations Density 0.161%

negations and their accompanying phrases

No Comments

No Known Activations