INDEX

Explanations

terms related to technical or scientific concepts, such as "expressive suppression," "neuroplasticity," and "reciprocity."

oai_token-act-pair · gpt-3.5-turbo

punctuation and conjunctions that indicate complex sentences or lists

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ubes

-0.75

arnaev

-0.74

Hours

-0.71

 Soon

-0.69

izens

-0.68

andals

-0.67

ãĥīãĥ©

-0.67

Shop

-0.66

swick

-0.66

azel

-0.66

POSITIVE LOGITS

 whereby

1.69

 wherein

1.45

aka

1.27

ie

1.23

 namely

1.17

 meaning

1.16

 which

1.15

1.03

 defined

0.99

 where

0.98

Activations Density 0.297%

terms related to technical or scientific concepts, such as "expressive suppression," "neuroplasticity," and "reciprocity."

punctuation and conjunctions that indicate complex sentences or lists

No Comments

No Known Activations