INDEX

Explanations

the phrase "make it."

oai_token-act-pair · gpt-3.5-turbo

phrases that repeatedly emphasize the pronoun "it" 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ACTIONS

-0.71

wcsstore

-0.66

idth

-0.66

":["

-0.63

othing

-0.60

 attachments

-0.60

 Magicka

-0.60

 Deaths

-0.55

 apologies

-0.55

 bells

-0.55

POSITIVE LOGITS

unes

0.88

chwitz

0.80

chy

0.74

ueller

0.74

self

0.72

iner

0.69

ocalypse

0.68

 abundantly

0.67

alia

0.67

 safer

0.66

Activations Density 0.073%

the phrase "make it."

phrases that repeatedly emphasize the pronoun "it" in various contexts

No Comments

No Known Activations