INDEX

Explanations

words related to trustworthiness and credibility

oai_token-act-pair · gpt-3.5-turbo

terms related to worthiness or merit

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ACA

-0.71

oan

-0.66

WAR

-0.66

eq

-0.65

udeb

-0.64

Wah

-0.63

ATHER

-0.61

hran

-0.60

ERA

-0.60

 Shank

-0.60

POSITIVE LOGITS

worthy

1.13

nesses

1.04

ness

0.89

lihood

0.87

orthy

0.74

worthiness

0.74

iaries

0.72

 worthy

0.70

otine

0.70

icles

0.69

Activations Density 0.012%

words related to trustworthiness and credibility

terms related to worthiness or merit

No Comments

No Known Activations