INDEX

Explanations

names of people or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names, possibly related to people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

udeb

-0.77

href

-0.77

¾

-0.75

 newsp

-0.74

Reviewer

-0.72

Magikarp

-0.72

SpaceEngineers

-0.71

catentry

-0.71

Interstitial

-0.69

ãĤ¦

-0.68

POSITIVE LOGITS

hower

0.80

 Sachs

0.74

 Dynamics

0.72

xtap

0.69

ashtra

0.69

kefeller

0.66

Eug

0.66

 Grove

0.64

wagen

0.64

 Banking

0.63

Activations Density 0.271%

names of people or organizations

proper nouns and names, possibly related to people or entities

No Comments

No Known Activations