INDEX

Explanations

words related to prominent individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "us."

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

ottest

-0.78

regor

-0.74

rought

-0.69

ITNESS

-0.65

¥ŀ

-0.65

ished

-0.64

td

-0.64

thening

-0.63

 livelihood

-0.63

jriwal

-0.63

POSITIVE LOGITS

pex

1.12

hee

0.96

peed

0.92

cules

0.91

pecting

0.88

aurus

0.88

cular

0.87

CRIP

0.87

pect

0.86

cus

0.85

Activations Density 0.031%

words related to prominent individuals

occurrences of the word "us."

No Comments

No Known Activations