INDEX

Explanations

phrases related to taking action or creating or manipulating something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "make" 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ©Ł

-0.78

anders

-0.68

stration

-0.64

ander

-0.64

rants

-0.63

moil

-0.62

Below

-0.62

thia

-0.62

hood

-0.61

 propensity

-0.60

POSITIVE LOGITS

 sure

1.66

 sense

0.99

 ends

0.95

 Sure

0.91

sure

0.90

 matters

0.89

 Sense

0.87

 room

0.79

 adjustments

0.78

 things

0.78

Activations Density 0.099%

phrases related to taking action or creating or manipulating something

instances of the word "make" in various contexts

No Comments

No Known Activations