INDEX

Explanations

phrases related to spatial location or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "at" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Palestinian

-0.67

aceutical

-0.62

Shell

-0.62

glass

-0.62

sett

-0.62

Russ

-0.61

legal

-0.58

eria

-0.58

ships

-0.58

PH

-0.58

POSITIVE LOGITS

 least

1.21

roph

0.86

 dusk

0.83

 random

0.83

onement

0.83

abase

0.82

 times

0.80

yp

0.80

las

0.79

 home

0.77

Activations Density 0.220%

phrases related to spatial location or position

occurrences of the word "at" in various contexts

No Comments

No Known Activations