INDEX

Explanations

references to the validity of something, such as email addresses, tickets, opinions, contracts, and IDs

oai_token-act-pair · gpt-3.5-turbo

instances of the word "valid" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ILA

-0.80

 Sisters

-0.75

hedon

-0.74

Mania

-0.67

hedral

-0.66

hani

-0.64

cipl

-0.63

HI

-0.62

azel

-0.62

OPS

-0.61

POSITIVE LOGITS

ating

0.97

 valid

0.93

ations

0.84

iated

0.84

ators

0.83

ifiable

0.79

ational

0.79

itimate

0.78

iation

0.78

ifying

0.76

Activations Density 0.004%

references to the validity of something, such as email addresses, tickets, opinions, contracts, and IDs

instances of the word "valid" in various contexts

No Known Activations