INDEX

Explanations

phrases related to forcing someone or something out of a place or position

oai_token-act-pair · gpt-3.5-turbo

phrases related to being removed or displaced from a location

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

leck

-0.73

paren

-0.69

 partName

-0.66

rien

-0.66

tips

-0.62

Catalog

-0.61

staking

-0.61

potion

-0.59

 counterpart

-0.58

 cues

-0.58

POSITIVE LOGITS

 rooft

0.79

 altogether

0.77

 rubble

0.74

 harms

0.74

 heel

0.70

âĸ¬

0.67

 Sabha

0.65

 Palest

0.65

 onto

0.65

het

0.64

Activations Density 0.117%

phrases related to forcing someone or something out of a place or position

phrases related to being removed or displaced from a location

No Comments

No Known Activations