INDEX

Explanations

phrases related to having the ability to reach a certain resource or information

oai_token-act-pair · gpt-3.5-turbo

references to access, particularly in the context of information or services

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

NR

-0.82

boxing

-0.80

NL

-0.79

soDeliveryDate

-0.77

need

-0.74

ernand

-0.73

roit

-0.72

okia

-0.71

Äĩ

-0.71

KK

-0.69

POSITIVE LOGITS

 assist

0.66

 minim

0.66

 preserve

0.66

 resources

0.66

 recess

0.64

 access

0.64

itives

0.64

 prevent

0.63

 lift

0.62

 riches

0.61

Activations Density 0.062%

phrases related to having the ability to reach a certain resource or information

references to access, particularly in the context of information or services

No Comments

No Known Activations