INDEX

Explanations

phrases that introduce a statement or perspective

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 nomine

-0.72

Js

-0.69

bush

-0.64

 tremend

-0.64

nec

-0.64

natureconservancy

-0.63

 Gong

-0.62

 Manufacturer

-0.61

erie

-0.60

 Sole

-0.59

POSITIVE LOGITS

 doubt

0.87

 doubts

0.76

ught

0.71

ado

0.71

 indication

0.67

 reminders

0.67

respect

0.65

 consistency

0.62

 semblance

0.61

 skepticism

0.60

Activations Density 0.062%

phrases that introduce a statement or perspective

phrases indicating uncertainty or speculation

No Comments

No Known Activations