INDEX

Explanations

names or terms related to diverse geographical locations

oai_token-act-pair · gpt-3.5-turbo

the patterns associated with specific names or terms related to Jewish identity and other associated identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ets

-0.95

ophers

-0.79

urable

-0.77

actic

-0.76

atever

-0.75

aunders

-0.74

artment

-0.74

awaru

-0.73

 mathemat

-0.72

tones

-0.72

POSITIVE LOGITS

 Scotia

0.85

ICAN

0.83

icans

0.79

éĹĺ

0.77

ism

0.73

 Giuliani

0.71

uda

0.71

~~~~

0.71

 Leban

0.70

 Ascend

0.69

Activations Density 0.011%

names or terms related to diverse geographical locations

the patterns associated with specific names or terms related to Jewish identity and other associated identities

No Comments

No Known Activations