INDEX

Explanations

phrases related to legal matters or actions

oai_token-act-pair · gpt-3.5-turbo

text that includes statistical or factual claims

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

 glim

-0.76

 Weiss

-0.75

Weiss

-0.75

 Atlas

-0.74

 Olson

-0.73

 Hemisphere

-0.72

 Beacon

-0.71

 Pennsylvania

-0.68

 Tulsa

-0.67

 Floyd

-0.67

POSITIVE LOGITS

jriwal

1.11

 Hindi

1.01

 Sharma

1.01

pta

1.00

umbai

0.98

 Bengal

0.97

 Delhi

0.95

 lakh

0.95

BJP

0.95

 Maharashtra

0.93

Activations Density 0.722%

phrases related to legal matters or actions

text that includes statistical or factual claims

No Comments

No Known Activations