INDEX

Explanations

the adverb 'still' indicating continuance or persistence

oai_token-act-pair · gpt-3.5-turbo

the repetitive use of the word "Still" at the beginning of statements

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

ãĥ³ãĤ¸

-0.79

 è£ıç

-0.71

alties

-0.69

incial

-0.68

duct

-0.64

psey

-0.64

ultimate

-0.62

ä»£

-0.62

rule

-0.61

ocol

-0.61

POSITIVE LOGITS

birth

0.77

noon

0.77

heres

0.73

 reeling

0.70

 retains

0.70

 technically

0.64

 retaining

0.64

Enjoy

0.64

 recovering

0.63

aked

0.63

Activations Density 0.025%

the adverb 'still' indicating continuance or persistence

the repetitive use of the word "Still" at the beginning of statements

No Comments

No Known Activations