INDEX

Explanations

terms related to physical locations or objects

oai_token-act-pair · gpt-3.5-turbo

references to various types of locations or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ertodd

-0.84

terday

-0.72

paces

-0.71

IUM

-0.71

emis

-0.69

DOM

-0.69

nir

-0.69

ymm

-0.67

ortium

-0.66

 Saban

-0.66

POSITIVE LOGITS

 practition

0.94

 dwell

0.85

 trips

0.81

 dwelling

0.78

 manners

0.77

 cleaner

0.77

 grad

0.76

 cleaning

0.74

 etiquette

0.73

 environments

0.72

Activations Density 0.390%

terms related to physical locations or objects

references to various types of locations or settings

No Comments

No Known Activations