INDEX

Explanations

phrases related to instructions or requirements

oai_token-act-pair · gpt-3.5-turbo

imperative statements or phrases that direct actions

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

oday

-0.64

pires

-0.63

burgh

-0.63

alf

-0.62

hum

-0.61

 Drum

-0.60

Ips

-0.60

Pi

-0.60

 Investor

-0.60

 Gord

-0.60

POSITIVE LOGITS

 manually

0.80

 understand

0.79

 beware

0.79

 kidding

0.79

 rely

0.77

 learn

0.76

itness

0.76

 yourself

0.74

 know

0.74

 specify

0.73

Activations Density 0.129%

phrases related to instructions or requirements

imperative statements or phrases that direct actions

No Comments

No Known Activations