INDEX

Explanations

words related to "help" or "helping"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word 'hel' and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Rated

-0.75

 retrospective

-0.69

 Flight

-0.62

CFR

-0.61

NTS

-0.61

 nomine

-0.60

displayText

-0.60

 incon

-0.59

 abnormal

-0.59

ItemTracker

-0.59

POSITIVE LOGITS

tered

1.07

hel

1.00

ters

0.96

pless

0.88

lehem

0.87

iman

0.87

mand

0.86

ping

0.86

anthrop

0.84

itism

0.84

Activations Density 0.008%

words related to "help" or "helping"

occurrences of the word 'hel' and its variations

No Comments

No Known Activations