INDEX

Explanations

comparative adjectives related to ranking or status

oai_token-act-pair · gpt-3.5-turbo

references to "second-class" or "third-class" status in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

XY

-0.68

Paper

-0.66

 Canaver

-0.66

Adams

-0.64

Rules

-0.63

stanbul

-0.61

IRC

-0.60

Reward

-0.60

GMT

-0.60

 Petraeus

-0.59

POSITIVE LOGITS

 baseman

1.21

arily

1.12

hand

1.09

isl

0.90

lege

0.82

aries

0.80

onyms

0.78

handedly

0.77

yrus

0.75

 responders

0.73

Activations Density 0.048%

comparative adjectives related to ranking or status

references to "second-class" or "third-class" status in various contexts

No Comments

No Known Activations