INDEX

Explanations

phrases containing the word "made"

oai_token-act-pair · gpt-3.5-turbo

the term "man-made" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

IRE

-0.78

AMS

-0.77

VERTISEMENT

-0.73

OUGH

-0.71

hus

-0.71

ECTION

-0.71

assis

-0.70

":["

-0.70

)].

-0.70

 FIRE

-0.68

POSITIVE LOGITS

Fake

0.80

 excuses

0.78

lda

0.68

userc

0.65

adjust

0.65

 interventions

0.63

 conspir

0.63

 discoveries

0.62

 excuse

0.62

artifacts

0.62

Activations Density 0.028%

phrases containing the word "made"

the term "man-made" in various contexts

No Comments

No Known Activations