INDEX

Explanations

words related to drugs or medical terms

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of algorithms and programming languages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lde

-0.73

itiveness

-0.71

SHIP

-0.68

glers

-0.67

fw

-0.66

elines

-0.64

hift

-0.64

 Cosponsors

-0.63

yip

-0.61

rers

-0.61

POSITIVE LOGITS

azeera

1.07

aeda

0.89

querque

0.88

arez

0.84

aida

0.83

hyde

0.74

abet

0.74

 Lama

0.71

way

0.69

Qaeda

0.69

Activations Density 0.062%

words related to drugs or medical terms

terms related to various types of algorithms and programming languages

No Comments

No Known Activations