INDEX

Explanations

phrases indicating a desire or action to push boundaries or take actions to a greater extent

oai_token-act-pair · gpt-3.5-turbo

expressions indicating progression or an increase in intensity

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

pected

-0.74

other

-0.69

 Cust

-0.65

ech

-0.62

esi

-0.61

ogy

-0.59

EMP

-0.59

 Warcraft

-0.59

 Sorce

-0.58

SEA

-0.58

POSITIVE LOGITS

 than

1.05

 distances

0.90

than

0.82

fetched

0.77

backer

0.73

awa

0.73

////////////////

0.69

 towards

0.69

 distance

0.68

 overboard

0.66

Activations Density 0.055%

phrases indicating a desire or action to push boundaries or take actions to a greater extent

expressions indicating progression or an increase in intensity

No Comments

No Known Activations