INDEX

Explanations

phrases related to first impressions

oai_token-act-pair · gpt-3.5-turbo

references to initial impressions or superficial observations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icer

-0.76

tailed

-0.73

ammy

-0.73

rus

-0.70

onement

-0.69

winter

-0.69

rop

-0.66

lez

-0.66

orders

-0.65

Joined

-0.65

POSITIVE LOGITS

 blush

0.89

 glance

0.89

 superf

0.84

 IMAGES

0.78

 premise

0.71

intuitive

0.67

 intuitive

0.66

ILD

0.65

ANE

0.64

 understandable

0.64

Activations Density 0.138%

phrases related to first impressions

references to initial impressions or superficial observations

No Comments

No Known Activations