INDEX

Explanations

the phrase "be it" followed by different scenarios or options

oai_token-act-pair · gpt-3.5-turbo

the word "it" used repeatedly 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.73

Texture

-0.71

devices

-0.70

ãĥ¼ãĥĨãĤ£

-0.65

 Polk

-0.61

ahead

-0.61

behind

-0.60

hips

-0.60

Band

-0.60

animal

-0.60

POSITIVE LOGITS

alian

1.18

chy

1.04

unes

0.94

self

0.91

anyahu

0.73

asca

0.72

ueller

0.71

henko

0.71

alm

0.71

zbollah

0.70

Activations Density 0.129%

the phrase "be it" followed by different scenarios or options

the word "it" used repeatedly in various contexts

No Comments

No Known Activations