INDEX

Explanations

phrases indicating anticipation or expectation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating future expectations or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

pac

-0.70

Cre

-0.66

redit

-0.66

killed

-0.64

adra

-0.64

parent

-0.63

ethyl

-0.63

processor

-0.61

Friends

-0.61

anium

-0.61

POSITIVE LOGITS

 CONTIN

0.98

 NEXT

0.75

 yourselves

0.72

 occasional

0.71

 plenty

0.70

 sometime

0.70

 yourself

0.67

sag

0.67

TW

0.66

 tomorrow

0.66

Activations Density 0.140%

phrases indicating anticipation or expectation

phrases indicating future expectations or predictions

No Comments

No Known Activations