INDEX

Explanations

news-related terms and entities

oai_token-act-pair · gpt-3.5-turbo

references to news entities or related terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iasis

-0.84

İĭ

-0.75

staking

-0.74

ACP

-0.68

uncle

-0.68

uras

-0.68

istic

-0.67

ism

-0.65

istically

-0.63

 Luther

-0.63

POSITIVE LOGITS

ashington

0.94

åº

0.92

hops

0.90

ynski

0.82

atcher

0.82

chool

0.81

hower

0.78

ource

0.76

ystem

0.75

peak

0.75

Activations Density 0.040%

news-related terms and entities

references to news entities or related terminology

No Comments

No Known Activations