INDEX

Explanations

negations combined with specific locations or contexts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exceptions or limitations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omas

-0.68

icides

-0.67

bath

-0.66

shown

-0.65

ihar

-0.62

icide

-0.61

inea

-0.61

inus

-0.59

ao

-0.59

ubi

-0.58

POSITIVE LOGITS

vous

0.66

ecast

0.63

hap

0.62

 Admir

0.61

atican

0.59

 ones

0.58

former

0.58

owitz

0.58

wives

0.57

 part

0.56

Activations Density 0.062%

negations combined with specific locations or contexts

phrases indicating exceptions or limitations

No Comments

No Known Activations