INDEX

Explanations

words related to political entities or organizations

oai_token-act-pair · gpt-3.5-turbo

segments of text that are entirely blank or contain minimal content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

terday

-0.92

 wise

-0.77

 sanity

-0.72

 parity

-0.70

theless

-0.68

etheless

-0.67

 unison

-0.66

 Extras

-0.65

 LAST

-0.63

 coupled

-0.62

POSITIVE LOGITS

onian

1.28

leys

1.04

intern

0.96

opian

0.95

orian

0.95

mans

0.93

osphere

0.93

seys

0.93

isphere

0.91

venth

0.90

Activations Density 0.254%

words related to political entities or organizations

segments of text that are entirely blank or contain minimal content

No Comments

No Known Activations