INDEX

Explanations

words related to losing or defeat

oai_token-act-pair · gpt-3.5-turbo

variations of the word "lose" in different contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Catalog

-0.64

orig

-0.64

 Patri

-0.63

"""

-0.62

cone

-0.61

 semin

-0.60

 Hale

-0.59

 respondent

-0.58

Paul

-0.58

 apolog

-0.58

POSITIVE LOGITS

luster

0.84

 Control

0.81

 control

0.77

itaire

0.75

odder

0.75

ffen

0.74

veyard

0.74

ittens

0.73

enthal

0.71

æ©

0.70

Activations Density 0.048%

words related to losing or defeat

variations of the word "lose" in different contexts

No Known Activations