INDEX

Explanations

references to individuals and their roles or positions

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

each

-0.82

these

-0.73

mares

-0.70

sheets

-0.70

rooms

-0.70

 solves

-0.69

their

-0.69

âĢķ

-0.69

thood

-0.68

ambo

-0.67

POSITIVE LOGITS

 largest

1.23

 oldest

1.20

 latest

1.15

 strongest

1.12

 fastest

1.11

 biggest

1.10

 highest

1.10

 culmination

1.09

 easiest

1.06

 cornerstone

1.06

Activations Density 0.152%

references to individuals and their roles or positions

the word "the" in various contexts

No Comments

No Known Activations