INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to specific names or terms, particularly those related to "Rig" or similar entities

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

 Hurricanes

-0.72

etheless

-0.71

terday

-0.69

 Despair

-0.68

 Peninsula

-0.66

\">

-0.65

 Hots

-0.63

ãĥĻ

-0.63

 Faul

-0.63

 Reagan

-0.63

POSITIVE LOGITS

glers

1.19

rig

1.07

gers

1.05

ging

1.05

idity

1.04

rid

1.03

rett

1.02

endum

1.00

ged

1.00

gin

0.97

Activations Density 0.020%

proper nouns

references to specific names or terms, particularly those related to "Rig" or similar entities

No Comments

No Known Activations