INDEX

Explanations

phrases indicating mathematical comparisons or inequalities

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

حوالہ

-0.61

 باخ

-0.60

 EconPapers

-0.59

 vigour

-0.58

 nakalista

-0.58

 ſaid

-0.58

ⓧ

-0.57

uário

-0.55

$_['

-0.55

 houſe

-0.54

POSITIVE LOGITS

leq

1.65

geq

1.34

leqslant

1.21

neq

1.13

geqslant

1.00

leqq

0.91

subseteq

0.90

≤

0.76

≤

0.69

subset

0.65

Activations Density 0.077%

phrases indicating mathematical comparisons or inequalities

No Comments

No Known Activations