INDEX

Explanations

verbs or phrases related to control, influence, or power

oai_token-act-pair · gpt-3.5-turbo

actions and phrases associated with negative consequences or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ortment

-0.70

oÄŁ

-0.67

âĹ¼

-0.67

ciplinary

-0.66

last

-0.61

alian

-0.61

tu

-0.60

utive

-0.59

eele

-0.58

 Approximately

-0.57

POSITIVE LOGITS

nor

1.57

 anymore

1.48

 anybody

1.46

 anything

1.34

 anyone

1.32

any

1.03

ANY

0.92

 slightest

0.91

 whatsoever

0.88

 anywhere

0.88

Activations Density 0.277%

verbs or phrases related to control, influence, or power

actions and phrases associated with negative consequences or situations

No Comments

No Known Activations