INDEX

Explanations

words related to perception, discernment, and inference

oai_token-act-pair · gpt-3.5-turbo

terms related to understanding and perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

href

-0.69

hyde

-0.64

zilla

-0.63

 Mehran

-0.61

 fixture

-0.60

 Medicare

-0.58

sche

-0.58

bish

-0.57

wife

-0.57

ammy

-0.57

POSITIVE LOGITS

ibly

0.98

ible

0.98

iour

0.86

ãĤ¨ãĥ«

0.82

ibles

0.79

orial

0.78

wered

0.77

ibility

0.74

MENTS

0.74

 Curve

0.73

Activations Density 0.032%

words related to perception, discernment, and inference

terms related to understanding and perception

No Comments

No Known Activations