INDEX

Explanations

phrases related to political or regulatory actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" and related prepositional phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ractor

-0.66

rov

-0.65

)*

-0.65

oola

-0.64

çĶ°

-0.64

!/

-0.64

ril

-0.63

rob

-0.62

oka

-0.62

cffffcc

-0.61

POSITIVE LOGITS

 lieu

1.15

 accordance

1.08

 Uganda

0.90

 Cambodia

0.90

 violation

0.85

 Thailand

0.85

 vitro

0.84

 Iraq

0.81

 Zimbabwe

0.81

 favor

0.79

Activations Density 0.429%

phrases related to political or regulatory actions

occurrences of the word "in" and related prepositional phrases

No Comments

No Known Activations