INDEX

Explanations

terms related to overlap or commonality among various concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

mybatisplus

-0.89

ContentAsync

-0.73

WindowConstants

-0.71

 postnatal

-0.69

LookAnd

-0.69

 للاسماء

-0.69

resizingMask

-0.69

 Италијани

-0.66

crollView

-0.65

Portály

-0.65

POSITIVE LOGITS

 overlap

1.13

 common

1.04

common

0.89

 overlaps

0.88

Common

0.80

 intersection

0.80

 Common

0.80

 overlapping

0.76

 shared

0.76

 overlapped

0.76

Activations Density 0.248%

terms related to overlap or commonality among various concepts or entities

No Comments

No Known Activations