INDEX

Explanations

comparisons using the word "like" followed by a description or analogy

oai_token-act-pair · gpt-3.5-turbo

comparisons and similes

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

 Cros

-0.85

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.71

 Glover

-0.68

©¶æ¥µ

-0.66

RAW

-0.64

[+

-0.63

CHAT

-0.62

ĳå£«

-0.62

 Whip

-0.62

Congratulations

-0.61

POSITIVE LOGITS

 than

1.53

than

1.33

 Than

1.05

erous

0.80

izable

0.70

cientious

0.69

istent

0.68

worldly

0.66

oldemort

0.62

nery

0.62

Activations Density 0.184%

comparisons using the word "like" followed by a description or analogy

comparisons and similes

No Comments

No Known Activations