INDEX

Explanations

word phrases indicating expressions, statements, or declarations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "telling."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

urdue

-0.83

cdn

-0.80

uld

-0.74

san

-0.70

engeance

-0.69

nam

-0.69

mun

-0.68

emetery

-0.68

Jump

-0.67

rane

-0.67

POSITIVE LOGITS

tale

1.17

ingly

0.88

tell

0.77

 tales

0.75

tons

0.72

 Tell

0.70

 tale

0.70

us

0.66

 aloud

0.66

 tell

0.65

Activations Density 0.013%

word phrases indicating expressions, statements, or declarations

instances of the word "telling."

No Comments

No Known Activations