INDEX

Explanations

words related to interactions or intersections

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "inter."

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

avorite

-0.72

Magikarp

-0.67

\\\\\\\\

-0.66

cffff

-0.66

 Skydragon

-0.65

aimon

-0.64

ORK

-0.63

unks

-0.62

Ã±

-0.62

¥µ

-0.62

POSITIVE LOGITS

mediate

1.03

ventions

0.86

actively

0.85

active

0.85

mitt

0.84

lace

0.79

vention

0.78

quart

0.74

stice

0.74

sect

0.74

Activations Density 0.006%

words related to interactions or intersections

instances of the substring "inter."

No Comments

No Known Activations