INDEX

Explanations

words related to the concept of "use"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "use" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inas

-0.68

owler

-0.67

ccording

-0.67

 toget

-0.67

alos

-0.66

igans

-0.62

awa

-0.61

arious

-0.61

inosaur

-0.61

oreal

-0.60

POSITIVE LOGITS

ppe

0.96

ibility

0.83

fully

0.82

fulness

0.79

lda

0.77

llo

0.75

Film

0.73

ãĥ¯

0.72

iculture

0.71

mble

0.71

Activations Density 0.032%

words related to the concept of "use"

occurrences of the word "use" and its variations

No Comments

No Known Activations