INDEX

Explanations

phrases related to physical or medical conditions that often have negative connotations

oai_token-act-pair · gpt-3.5-turbo

instances of the letter "l" 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 @ 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

éĹĺ

-0.86

ãĥ¼ãĥĨãĤ£

-0.79

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.78

OLOGY

-0.72

ãĥ¼ãĤ¯

-0.71

 Primal

-0.71

ãĥ¯ãĥ³

-0.69

ãĤ®

-0.68

å§«

-0.66

 Parenthood

-0.66

POSITIVE LOGITS

adders

1.31

ibr

1.23

ugs

1.19

ibrarian

1.16

ashes

1.14

ipp

1.13

ips

1.13

idd

1.12

isted

1.09

asso

1.08

Activations Density 0.019%

phrases related to physical or medical conditions that often have negative connotations

instances of the letter "l" in various contexts

No Comments

No Known Activations