INDEX

Explanations

phrases related to barriers or restrictions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating barriers or restrictions

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

 tune

-0.81

 tunes

-0.71

requency

-0.68

enos

-0.65

ovie

-0.65

 fare

-0.61

acus

-0.61

oice

-0.60

rative

-0.60

MON

-0.60

POSITIVE LOGITS

 airspace

0.93

 Borders

0.89

 borders

0.85

 confines

0.85

 perimeter

0.83

 porous

0.79

 encl

0.76

agall

0.76

taboola

0.70

 secrecy

0.70

Activations Density 0.317%

phrases related to barriers or restrictions

phrases indicating barriers or restrictions

No Comments

No Known Activations