INDEX

Explanations

phrases related to new or incoming items or events

oai_token-act-pair · gpt-3.5-turbo

terms related to incoming information or data streams

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

arist

-0.82

©¶æ

-0.77

ching

-0.75

arily

-0.75

mel

-0.72

agra

-0.71

ARC

-0.69

ifications

-0.69

elling

-0.69

ifiable

-0.68

POSITIVE LOGITS

 arrivals

0.82

 outgoing

0.78

 freshmen

0.78

ãģŁ

0.78

ãĤĬ

0.72

 incoming

0.71

 arrival

0.70

oing

0.69

aukee

0.69

lus

0.67

Activations Density 0.019%

phrases related to new or incoming items or events

terms related to incoming information or data streams

No Comments

No Known Activations