INDEX

Explanations

proper nouns or specific entities

oai_token-act-pair · gpt-3.5-turbo

the word "the" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

thood

-0.72

iffe

-0.71

earch

-0.70

leeve

-0.69

rehend

-0.68

Background

-0.67

rade

-0.67

verage

-0.66

eno

-0.64

hire

-0.64

POSITIVE LOGITS

oret

1.23

 latter

1.18

 longest

1.16

 shortest

1.14

 same

1.11

 fastest

1.11

 biggest

1.09

 smallest

1.08

 largest

1.07

 simplest

1.07

Activations Density 0.168%

proper nouns or specific entities

the word "the" in various contexts

No Comments

No Known Activations