INDEX

Explanations

words related to the concept of impact

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "impact."

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

Bav

-0.75

corn

-0.70

ubes

-0.67

wagen

-0.66

vision

-0.63

chen

-0.63

ymph

-0.62

IDE

-0.62

 whisk

-0.62

 subp

-0.61

POSITIVE LOGITS

 impact

1.02

ful

1.00

impact

0.94

 impacts

0.94

 crater

0.89

eless

0.88

effects

0.82

alore

0.81

iveness

0.77

 impacted

0.76

Activations Density 0.028%

words related to the concept of impact

references to the concept of "impact."

No Comments

No Known Activations