INDEX

Explanations

instances of the word "looking."

oai_token-act-pair · gpt-3.5-turbo

repeated phrases indicating a desire to seek or obtain something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

SPONSORED

-0.60

cia

-0.59

ced

-0.58

 Split

-0.58

 Verse

-0.57

WN

-0.57

 Synd

-0.56

MQ

-0.56

MS

-0.55

Truth

-0.55

POSITIVE LOGITS

 forward

0.79

 suspic

0.78

ahead

0.75

ãĤ¶

0.72

 ahead

0.69

ocene

0.67

 squarely

0.66

irection

0.65

 geared

0.64

ldon

0.64

Activations Density 0.035%

instances of the word "looking."

repeated phrases indicating a desire to seek or obtain something

No Comments

No Known Activations