INDEX

Explanations

instances where someone is recalling or reacting to new information

oai_token-act-pair · gpt-3.5-turbo

instances of the phrases related to hearing and learning new information

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

ometimes

-0.80

except

-0.75

ccording

-0.73

umerous

-0.72

 entirely

-0.70

unless

-0.68

COMPLE

-0.67

 unparalleled

-0.67

aples

-0.67

actly

-0.66

POSITIVE LOGITS

my

0.67

 puberty

0.61

 Wings

0.59

 Deadline

0.59

 this

0.58

 Pist

0.57

 goodbye

0.57

 Sloan

0.56

 Flower

0.56

 graduation

0.56

Activations Density 0.252%

instances where someone is recalling or reacting to new information

instances of the phrases related to hearing and learning new information

No Comments

No Known Activations