INDEX

Explanations

phrases related to the use of various technologies or techniques

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "used" 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 @ 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

Not in Any Lists

No Comments

Negative Logits

Hai

-0.77

awk

-0.71

rats

-0.71

dom

-0.70

gdala

-0.68

antle

-0.67

 Tale

-0.65

odore

-0.64

mares

-0.62

ortality

-0.60

POSITIVE LOGITS

fully

0.86

 Used

0.84

 sparing

0.82

 condoms

0.75

FUL

0.74

heny

0.70

ivated

0.67

 interchange

0.66

 tools

0.65

 aback

0.65

Activations Density 0.047%

phrases related to the use of various technologies or techniques

occurrences of the word "used" in various contexts

No Comments

No Known Activations