INDEX

Explanations

phrases indicating a comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that" indicating referencing or elaboration

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

Jam

-0.80

Bow

-0.79

 Corpus

-0.73

CBC

-0.72

Pri

-0.72

MAP

-0.69

christ

-0.68

kay

-0.67

hip

-0.67

Gy

-0.66

POSITIVE LOGITS

 haun

0.81

yip

0.78

 transc

0.74

 consumes

0.74

ivia

0.71

oker

0.71

 perme

0.70

ItemTracker

0.70

 resolves

0.68

warts

0.68

Activations Density 0.075%

phrases indicating a comparison or contrast

instances of the word "that" indicating referencing or elaboration

No Comments

No Known Activations