INDEX

Explanations

phrases related to someone expressing a statement or opinion

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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

EMBER

-0.71

andem

-0.63

IELD

-0.62

tails

-0.62

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.62

SHA

-0.60

izont

-0.59

gments

-0.59

STE

-0.59

arest

-0.59

POSITIVE LOGITS

 although

0.82

 sounded

0.75

"[

0.69

 contradicts

0.68

'[

0.68

 preceded

0.65

 whilst

0.63

"#

0.63

 they

0.62

amera

0.61

Activations Density 0.217%

phrases related to someone expressing a statement or opinion

the word "that" in various contexts

No Comments

No Known Activations