INDEX

Explanations

the word "front" in the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "in front."

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

cci

-0.92

zie

-0.82

IRO

-0.75

Rating

-0.73

assets

-0.73

chini

-0.72

 Flavoring

-0.71

vil

-0.70

cano

-0.70

ARP

-0.70

POSITIVE LOGITS

 facing

0.74

ed

0.74

row

0.71

 teeth

0.70

eering

0.67

runners

0.66

ocrin

0.66

office

0.66

sburg

0.65

 yard

0.65

Activations Density 0.010%

the word "front" in the text

occurrences of the phrase "in front."

No Comments

No Known Activations