INDEX

Explanations

words related to locations or organizations

oai_token-act-pair · gpt-3.5-turbo

words related to accountability

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

JV

-0.80

hua

-0.73

PB

-0.72

hyde

-0.67

SG

-0.66

LM

-0.65

PLA

-0.65

geist

-0.65

knife

-0.64

ben

-0.64

POSITIVE LOGITS

uracy

1.23

redited

1.11

identally

1.00

urate

0.99

uzz

0.99

inations

0.95

idental

0.94

ustomed

0.92

acies

0.91

urrency

0.90

Activations Density 0.011%

words related to locations or organizations

words related to accountability

No Comments

No Known Activations