INDEX

Explanations

proper names, particularly focusing on individuals named "Janet"

oai_token-act-pair · gpt-3.5-turbo

references to individuals named Janet or Betsy

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

Interstitial

-0.99

Sov

-0.78

doors

-0.74

FTWARE

-0.72

gran

-0.67

amaz

-0.67

juven

-0.64

taboola

-0.64

fare

-0.64

POSITIVE LOGITS

 Mock

1.00

 Janet

0.96

ovic

0.79

 Nicol

0.78

 Reno

0.76

ellen

0.73

clips

0.72

 Jackson

0.72

ovan

0.71

 Walton

0.71

Activations Density 0.009%

proper names, particularly focusing on individuals named "Janet"

references to individuals named Janet or Betsy

No Comments

No Known Activations