INDEX

Explanations

words related to physical conflicts or disputes

oai_token-act-pair · gpt-3.5-turbo

terms related to conflict and altercations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

eele

-0.76

arton

-0.72

akeru

-0.70

undai

-0.70

 stocking

-0.64

Commerce

-0.62

idge

-0.62

ricia

-0.60

ographies

-0.60

POSITIVE LOGITS

 between

1.27

 ensued

1.19

 raged

1.07

 raging

1.06

 waged

0.99

between

0.98

 erupted

0.93

SHIP

0.90

 pits

0.89

 against

0.88

Activations Density 0.213%

words related to physical conflicts or disputes

terms related to conflict and altercations

No Comments

No Known Activations