INDEX

Explanations

references to "gaps" between different entities in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to disparities or differences, particularly focusing on the concept of a "gap."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

der

-0.71

vez

-0.63

prise

-0.63

ocations

-0.61

di

-0.61

ise

-0.60

ivery

-0.60

rich

-0.59

Die

-0.58

asting

-0.57

POSITIVE LOGITS

 between

1.12

wid

1.02

between

1.00

gap

0.92

 Between

0.92

 widened

0.90

 separating

0.82

 widen

0.80

Gap

0.77

 junction

0.77

Activations Density 0.039%

references to "gaps" between different entities in various contexts

terms related to disparities or differences, particularly focusing on the concept of a "gap."

No Comments

No Known Activations