INDEX

Explanations

names or terms related to individuals or organizations, particularly emphasizing 'Ol'

oai_token-act-pair · gpt-3.5-turbo

the name "Ol" referenced multiple times in various contexts

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

ãĥ¼ãĥĨãĤ£

-0.87

CFR

-0.72

Øª

-0.70

 IEEE

-0.69

Uncommon

-0.66

liness

-0.66

plane

-0.64

 Whitman

-0.64

 Ø§ÙĦ

-0.64

EEE

-0.64

POSITIVE LOGITS

sen

0.91

iver

0.90

athe

0.89

atile

0.88

imar

0.87

kil

0.86

mer

0.85

ipop

0.85

okia

0.85

alia

0.84

Activations Density 0.018%

names or terms related to individuals or organizations, particularly emphasizing 'Ol'

the name "Ol" referenced multiple times in various contexts

No Comments

No Known Activations