INDEX

Explanations

words related to conflicts or instances of being conflicted

oai_token-act-pair · gpt-3.5-turbo

the word "confusion" and its variants

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

senal

-0.99

BALL

-0.79

OHN

-0.74

matically

-0.74

fare

-0.73

NING

-0.70

matical

-0.70

minecraft

-0.70

GY

-0.68

schild

-0.67

POSITIVE LOGITS

licts

1.43

idential

1.42

irmed

1.39

irmation

1.39

luence

1.36

licted

1.27

lict

1.27

irming

1.26

erences

1.24

irms

1.23

Activations Density 0.029%

words related to conflicts or instances of being conflicted

the word "confusion" and its variants

No Comments

No Known Activations