INDEX

Explanations

words related to neutrality

oai_token-act-pair · gpt-3.5-turbo

references to neutrality and neutral perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.96

 millenn

-0.81

Mill

-0.78

INFO

-0.77

HAEL

-0.74

Hop

-0.74

Amazing

-0.72

URE

-0.72

Bio

-0.71

URES

-0.71

POSITIVE LOGITS

izing

1.04

izers

1.02

ization

1.02

izer

0.96

izes

0.95

utral

0.91

itÃ©

0.90

ize

0.89

ized

0.85

 neutral

0.85

Activations Density 0.017%

words related to neutrality

references to neutrality and neutral perspectives

No Comments

No Known Activations