INDEX

Explanations

phrases indicating strong opinions or evaluations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the significance or impact of events or statements

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

anus

-0.64

 celebrated

-0.63

 consulted

-0.59

itable

-0.57

uled

-0.56

 prototypes

-0.55

oided

-0.55

anz

-0.54

schild

-0.54

 renovations

-0.54

POSITIVE LOGITS

emi

0.72

argo

0.65

Jr

0.65

HO

0.64

 credibility

0.64

 causation

0.62

 alot

0.62

âĢ¦)

0.61

Uk

0.61

 cred

0.61

Activations Density 0.534%

phrases indicating strong opinions or evaluations

phrases indicating the significance or impact of events or statements

No Comments

No Known Activations