INDEX

Explanations

phrases indicating requirements or instructions

oai_token-act-pair · gpt-3.5-turbo

phrases expressing necessity or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Ń·

-0.64

 Democr

-0.63

 Dism

-0.62

 delinqu

-0.62

crime

-0.60

terness

-0.60

 Sounds

-0.59

berra

-0.58

 Pill

-0.58

emies

-0.57

POSITIVE LOGITS

lessly

1.17

nces

0.77

 convincing

0.72

xus

0.71

OTH

0.68

 patience

0.67

ache

0.67

esome

0.67

 assistance

0.67

 accommodations

0.66

Activations Density 0.060%

phrases indicating requirements or instructions

phrases expressing necessity or requirements

No Comments

No Known Activations