INDEX

Explanations

proper nouns related to an organization or location named "Congo."

oai_token-act-pair · gpt-3.5-turbo

references to the word "Cong" and related terms in various contexts

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

ãĤ´ãĥ³

-0.85

 Marketable

-0.79

 Leilan

-0.78

IPS

-0.77

 Gleaming

-0.74

 logger

-0.69

pmwiki

-0.69

OHN

-0.67

 SPORTS

-0.67

fulness

-0.67

POSITIVE LOGITS

regation

1.15

 Cong

1.14

cong

1.08

regate

1.07

ressive

1.03

rats

1.00

ression

0.96

reg

0.95

Cong

0.90

andan

0.90

Activations Density 0.010%

proper nouns related to an organization or location named "Congo."

references to the word "Cong" and related terms in various contexts

No Comments

No Known Activations