INDEX

Explanations

phrases indicating a change or transformation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "turn" and its variations 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

è¦ļéĨĴ

-0.90

andan

-0.61

hess

-0.59

 Expansion

-0.57

ority

-0.57

foundation

-0.56

 constitu

-0.56

den

-0.55

DAQ

-0.54

bons

-0.54

POSITIVE LOGITS

around

0.92

 inward

0.77

Ī

0.77

 into

0.76

coat

0.76

 around

0.72

 tide

0.69

 heads

0.68

 INTO

0.67

 Tide

0.67

Activations Density 0.035%

phrases indicating a change or transformation

instances of the word "turn" and its variations in various contexts

No Comments

No Known Activations