INDEX

Explanations

references to the word "honey"

oai_token-act-pair · gpt-3.5-turbo

references to honey 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

osure

-0.87

aneous

-0.84

uers

-0.81

ative

-0.81

ATIONS

-0.80

aneously

-0.76

ŃĶ

-0.73

ividual

-0.69

andals

-0.68

ista

-0.67

POSITIVE LOGITS

moon

1.35

bees

1.21

bee

1.10

comb

1.05

bee

1.05

 bees

0.94

 honey

0.92

 Honey

0.91

Bee

0.89

pots

0.86

Activations Density 0.011%

references to the word "honey"

references to honey in various contexts

No Comments

No Known Activations