INDEX

Explanations

phrases or words related to logical reasoning or justification

oai_token-act-pair · gpt-3.5-turbo

occurrences and mentions of the concept of "reason."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avorite

-0.77

 Carbuncle

-0.73

 Observer

-0.64

semble

-0.64

ibaba

-0.63

ModLoader

-0.62

omez

-0.60

arb

-0.60

eatures

-0.59

itals

-0.58

POSITIVE LOGITS

abl

1.36

ably

1.00

why

0.96

ality

0.83

boards

0.80

lessly

0.79

WHY

0.78

neum

0.77

ptr

0.77

why

0.76

Activations Density 0.033%

phrases or words related to logical reasoning or justification

occurrences and mentions of the concept of "reason."

No Comments

No Known Activations