INDEX

Explanations

text related to processing, particularly in relation to various contexts such as technology, payments, reports, and efficiency

oai_token-act-pair · gpt-3.5-turbo

references to the concept of processing

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

liest

-0.81

ortium

-0.72

gged

-0.70

sky

-0.70

gets

-0.70

legged

-0.69

lihood

-0.67

 Strat

-0.66

jah

-0.64

feat

-0.63

POSITIVE LOGITS

 Processing

1.00

 processing

0.96

IME

0.80

folios

0.79

 processors

0.77

avascript

0.77

utical

0.76

processing

0.76

 cones

0.74

 receipts

0.74

Activations Density 0.029%

text related to processing, particularly in relation to various contexts such as technology, payments, reports, and efficiency

references to the concept of processing

No Comments

No Known Activations