INDEX

Explanations

conjunctions 'and'

oai_token-act-pair · gpt-3.5-turbo

the word "and" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.74

SHIP

-0.71

ZA

-0.70

IUM

-0.67

Deal

-0.66

INST

-0.66

>[

-0.65

ORPG

-0.64

mania

-0.63

OTA

-0.63

POSITIVE LOGITS

 foremost

1.19

rogens

0.86

 brightest

0.81

rogen

0.78

 fateful

0.77

 cheapest

0.72

 simplest

0.70

 secondly

0.69

liest

0.69

 wealthiest

0.69

Activations Density 0.073%

conjunctions 'and'

the word "and" in various contexts

No Comments

No Known Activations