INDEX

Explanations

instances of the word "unable" and related expressions of inability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 suprême

-0.66

colgroup

-0.66

 présidenti

-0.62

 समीक्षाएं

-0.62

SequentialGroup

-0.61

 referenties

-0.60

ENTINA

-0.59

becken

-0.58

 Behör

-0.58

 littéraire

-0.58

POSITIVE LOGITS

 cannot

0.69

Hochspringen

0.65

无法

0.62

 unemployment

0.61

 cant

0.61

Phi

0.61

 unable

0.61

無法

0.59

 Cant

0.56

 Unable

0.55

Activations Density 0.152%

instances of the word "unable" and related expressions of inability

No Comments

No Known Activations