INDEX

Explanations

financial or quantitative terms related to adjustment or balancing

oai_token-act-pair · gpt-3.5-turbo

terminology related to offsets in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Export

-0.77

Interstitial

-0.70

CRIP

-0.67

zech

-0.65

pload

-0.64

uscript

-0.64

KER

-0.63

asts

-0.62

wordpress

-0.62

NetMessage

-0.61

POSITIVE LOGITS

ting

1.23

mented

0.96

ments

0.91

ment

0.87

ted

0.80

aneous

0.80

balance

0.78

balanced

0.74

aria

0.74

minist

0.73

Activations Density 0.010%

financial or quantitative terms related to adjustment or balancing

terminology related to offsets in various contexts

No Comments

No Known Activations