INDEX

Explanations

phrases related to accumulation and increase

oai_token-act-pair · gpt-3.5-turbo

phrases or contexts related to growth or accumulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ught

-0.77

hiro

-0.72

nor

-0.68

mens

-0.66

gee

-0.64

my

-0.63

pull

-0.62

grim

-0.62

 pierced

-0.62

cut

-0.61

POSITIVE LOGITS

river

0.81

dates

0.79

undown

0.77

react

0.71

 friendships

0.70

amina

0.70

 tents

0.69

ivism

0.67

grades

0.66

 sleeves

0.65

Activations Density 0.039%

phrases related to accumulation and increase

phrases or contexts related to growth or accumulation

No Comments

No Known Activations