INDEX

Explanations

phrases related to different types of trees, especially the word "Pine."

oai_token-act-pair · gpt-3.5-turbo

references to "pine" in various contexts, including trees, cones, and food

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

ioch

-0.73

enance

-0.73

Interstitial

-0.72

HCR

-0.69

hered

-0.67

Money

-0.67

=""

-0.66

DERR

-0.66

########

-0.65

ivation

-0.65

POSITIVE LOGITS

apple

1.27

cone

1.17

phrine

1.01

 cones

0.95

stal

0.89

lla

0.89

 pine

0.88

 cone

0.87

berry

0.82

ll

0.79

Activations Density 0.026%

phrases related to different types of trees, especially the word "Pine."

references to "pine" in various contexts, including trees, cones, and food

No Comments

No Known Activations