INDEX

Explanations

phrases related to scheduling or planning events

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of 'hedge' or 'hedging'

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

é¾įå

-0.70

 STOR

-0.61

ESSION

-0.60

ACP

-0.59

ESS

-0.59

CTR

-0.59

VW

-0.59

 Legions

-0.57

 Magnum

-0.56

DEF

-0.55

POSITIVE LOGITS

tons

1.00

ding

0.98

rina

0.83

rical

0.82

dar

0.82

uled

0.81

aily

0.80

rosis

0.80

ĪĴ

0.77

hai

0.77

Activations Density 0.017%

phrases related to scheduling or planning events

words related to the concept of 'hedge' or 'hedging'

No Comments

No Known Activations