INDEX

Explanations

the word "Whatever" followed by different contexts or situations

oai_token-act-pair · gpt-3.5-turbo

the use of the word "whatever" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ciating

-0.71

ellar

-0.64

osp

-0.61

arie

-0.61

arium

-0.59

ARS

-0.59

"},"

-0.59

rals

-0.56

atin

-0.56

nee

-0.55

POSITIVE LOGITS

theless

0.77

 foregoing

0.75

 disclaim

0.67

 Factors

0.67

 dissu

0.66

 uncertainties

0.66

 biases

0.65

ommel

0.64

 interpretation

0.63

 endif

0.63

Activations Density 0.070%

the word "Whatever" followed by different contexts or situations

the use of the word "whatever" and its variations

No Comments

No Known Activations