INDEX

Explanations

verbs related to significant changes or conversions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "transform" in various contexts

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

PLIED

-0.67

xia

-0.66

 LIMITED

-0.66

REL

-0.65

ramid

-0.65

bis

-0.62

 WARN

-0.59

cheat

-0.59

 Lists

-0.59

 Reasons

-0.58

POSITIVE LOGITS

ively

0.86

atile

0.85

 transform

0.83

 transforms

0.83

ives

0.81

ational

0.79

 transformations

0.77

atform

0.76

 transformation

0.73

idable

0.73

Activations Density 0.020%

verbs related to significant changes or conversions

instances of the word "transform" in various contexts

No Comments

No Known Activations