INDEX

Explanations

words indicating purpose or aim

oai_token-act-pair · gpt-3.5-turbo

expressions related to intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cit

-0.84

java

-0.67

 Solitaire

-0.64

 Tycoon

-0.64

visors

-0.63

 Figures

-0.63

 Medals

-0.59

 Kerr

-0.59

 Wolves

-0.59

hill

-0.58

POSITIVE LOGITS

ality

1.07

ful

0.96

lessly

0.87

reprene

0.85

phis

0.84

fulness

0.82

edly

0.81

ually

0.81

ual

0.74

ãĥĨ

0.74

Activations Density 0.022%

words indicating purpose or aim

expressions related to intentions

No Comments

No Known Activations