INDEX

Explanations

words related to surprising or shocking events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "shocked" and similar reactions to surprising events

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

amins

-1.00

emis

-0.86

folios

-0.84

ciplinary

-0.83

iosyncr

-0.82

ately

-0.76

pmwiki

-0.73

ships

-0.73

 ende

-0.72

resso

-0.71

POSITIVE LOGITS

à¤¾

0.77

 onlook

0.73

 bystanders

0.72

ingly

0.71

ãĤ¦ãĤ¹

0.71

 shocked

0.71

wave

0.70

 silence

0.70

 Corbyn

0.70

waves

0.67

Activations Density 0.021%

words related to surprising or shocking events

instances of the word "shocked" and similar reactions to surprising events

No Comments

No Known Activations