INDEX

Explanations

mentions of the time period "decade."

oai_token-act-pair · gpt-3.5-turbo

references to the concept of a decade

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

ournals

-0.81

 ingred

-0.71

iqu

-0.69

iquid

-0.68

anamo

-0.67

 procedural

-0.66

perse

-0.66

hammad

-0.66

hemat

-0.64

room

-0.64

POSITIVE LOGITS

ago

0.94

 ILCS

0.90

Ago

0.76

uously

0.75

ĸļ

0.72

 Anniversary

0.72

icity

0.71

 onward

0.70

ary

0.70

èĪ

0.68

Activations Density 0.026%

mentions of the time period "decade."

references to the concept of a decade

No Comments

No Known Activations