INDEX

Explanations

the verb 'assume' and variations of it

oai_token-act-pair · gpt-3.5-turbo

instances of the word "assume" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

HCR

-0.79

psey

-0.79

turn

-0.78

sung

-0.76

gom

-0.76

cgi

-0.73

waters

-0.67

ingen

-0.67

nels

-0.67

agra

-0.66

POSITIVE LOGITS

 assume

0.77

 incorrectly

0.75

 innocence

0.73

 ownership

0.73

 assumed

0.71

 responsibility

0.67

 RESP

0.66

ially

0.66

 assumptions

0.66

 Cortana

0.66

Activations Density 0.036%

the verb 'assume' and variations of it

instances of the word "assume" and related variations

No Comments

No Known Activations