INDEX

Explanations

words indicating direction or orientation

oai_token-act-pair · gpt-3.5-turbo

directional movements or movements towards a specific point

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

quest

-0.74

eria

-0.71

oner

-0.68

ERY

-0.68

 Offic

-0.67

ulet

-0.67

 Younger

-0.66

pkg

-0.66

orah

-0.65

Database

-0.65

POSITIVE LOGITS

 perpendicular

1.08

 orbit

1.06

wards

0.97

 curv

0.97

 distances

0.96

 orbits

0.96

 axis

0.93

 curved

0.91

 distance

0.90

 circular

0.90

Activations Density 0.365%

words indicating direction or orientation

directional movements or movements towards a specific point

No Comments

No Known Activations