INDEX

Explanations

words related to information

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "inf," indicating a focus on words related to influence or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hyde

-0.77

å§«

-0.75

BOOK

-0.73

 Blitz

-0.72

OPLE

-0.71

soDeliveryDate

-0.71

manship

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.67

DragonMagazine

-0.67

Downloadha

-0.66

POSITIVE LOGITS

requent

1.15

requently

1.15

usions

1.15

raction

1.14

ractions

1.13

idelity

1.09

luence

1.06

estation

1.05

erno

1.04

acqu

1.03

Activations Density 0.008%

words related to information

instances of the prefix "inf," indicating a focus on words related to influence or impact

No Comments

No Known Activations