INDEX

Explanations

phrases related to exclusivity or permission

oai_token-act-pair · gpt-3.5-turbo

negations or expressions of denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Fuji

-0.69

 Gaul

-0.67

 casc

-0.66

 Jihad

-0.60

 simultane

-0.59

 Riding

-0.58

 Cyan

-0.58

 hurd

-0.58

 Drawn

-0.58

 Crossing

-0.57

POSITIVE LOGITS

1.11

ï¸ı

0.94

tal

0.94

ves

0.93

ude

0.92

ve

0.90

tarian

0.89

vest

0.87

ieve

0.86

Activations Density 0.157%

phrases related to exclusivity or permission

negations or expressions of denial

No Comments

No Known Activations