INDEX

Explanations

questions starting with "How is...?" or "How does...?"

oai_token-act-pair · gpt-3.5-turbo

interrogative phrases that seek clarification or information

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

HB

-0.69

 Flags

-0.65

 Islands

-0.62

DAQ

-0.61

 Skydragon

-0.61

Area

-0.61

Flags

-0.60

Uncommon

-0.60

ipel

-0.60

POSITIVE LOGITS

?]

0.73

olate

0.69

doi

0.64

anchester

0.64

 heck

0.63

?),

0.62

 discipl

0.61

 reconcil

0.59

iliate

0.59

hester

0.59

Activations Density 0.033%

questions starting with "How is...?" or "How does...?"

interrogative phrases that seek clarification or information

No Comments

No Known Activations