INDEX

Explanations

words related to locations or actions involving the action of 'picking'

oai_token-act-pair · gpt-3.5-turbo

words related to specific locations and historical events

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

BuyableInstoreAndOnline

-0.88

ATIONAL

-0.82

 unfocusedRange

-0.71

ATTLE

-0.66

ANC

-0.66

 warr

-0.66

ãĥ´ãĤ¡

-0.65

 Windsor

-0.64

Ton

-0.64

 Sparkle

-0.64

POSITIVE LOGITS

ilver

1.26

haw

1.25

icks

1.16

hire

1.01

icking

0.96

etts

0.93

ety

0.92

hift

0.87

eter

0.86

ense

0.85

Activations Density 0.012%

words related to locations or actions involving the action of 'picking'

words related to specific locations and historical events

No Comments

No Known Activations