INDEX

Explanations

mentions of indicators, both in literal and metaphorical contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to indicators and measurements of various qualities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

frey

-0.87

atche

-0.80

oÄŁ

-0.75

LOAD

-0.74

POSE

-0.72

©¶æ

-0.71

zens

-0.69

ski

-0.69

halla

-0.69

ENG

-0.68

POSITIVE LOGITS

 indicators

1.20

 indicator

1.07

 gauge

0.84

 markers

0.84

 Signs

0.73

gau

0.72

ially

0.72

icators

0.71

 marker

0.70

measures

0.67

Activations Density 0.024%

mentions of indicators, both in literal and metaphorical contexts

terms related to indicators and measurements of various qualities or conditions

No Comments

No Known Activations