INDEX

Explanations

mentions of the word "cher" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to people or characters with the name "Cher."

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

¥µ

-0.68

undo

-0.67

ension

-0.65

Reviewer

-0.63

onent

-0.62

eworks

-0.62

opathy

-0.62

condition

-0.60

endum

-0.60

opal

-0.60

POSITIVE LOGITS

cher

1.02

chers

0.91

eers

0.87

ry

0.85

ãĤ¡

0.80

mann

0.80

tons

0.78

lain

0.78

pine

0.78

sonian

0.77

Activations Density 0.016%

mentions of the word "cher" in various contexts

references to people or characters with the name "Cher."

No Comments

No Known Activations