INDEX

Explanations

specific pronouns

oai_token-act-pair · gpt-3.5-turbo

the word "those" 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

kamp

-0.77

ob

-0.75

ILY

-0.74

 Ness

-0.73

onis

-0.68

achus

-0.67

Â¨

-0.67

iness

-0.66

OB

-0.65

Drag

-0.65

POSITIVE LOGITS

 pesky

1.19

 kinds

1.04

 sorts

0.92

 fateful

0.85

 sights

0.78

 aforementioned

0.75

 thoughts

0.74

 damned

0.74

 same

0.73

 types

0.72

Activations Density 0.067%

specific pronouns

the word "those" in various contexts

No Comments

No Known Activations