INDEX

Explanations

phrases expressing negative emotions or unfortunate situations

oai_token-act-pair · gpt-3.5-turbo

expressions of sorrow or regret

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

afort

-0.82

uese

-0.81

 newsp

-0.79

insula

-0.78

amins

-0.76

enture

-0.74

ual

-0.73

uality

-0.72

 Gutenberg

-0.71

itives

-0.71

POSITIVE LOGITS

 sadly

0.79

à¥

0.78

ãĥ©ãĥ³

0.73

ãĤ´ãĥ³

0.73

 parted

0.70

ãĥĲ

0.70

 displayed

0.69

à¤¾

0.69

stal

0.67

Activations Density 0.024%

phrases expressing negative emotions or unfortunate situations

expressions of sorrow or regret

No Comments

No Known Activations