INDEX

Explanations

the word "Kumar"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Kumar" and its variations in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tower

-0.80

swick

-0.77

 Erie

-0.76

hops

-0.74

mble

-0.73

bley

-0.72

xp

-0.72

htaking

-0.70

glers

-0.69

ternally

-0.67

POSITIVE LOGITS

 Sharma

1.21

 Gupta

1.14

pour

1.09

 Singh

0.98

 Kumar

0.94

 Modi

0.94

 Patel

0.91

Rao

0.86

 Pradesh

0.85

 Gandhi

0.85

Activations Density 0.065%

the word "Kumar"

occurrences of the name "Kumar" and its variations in the text

No Comments

No Known Activations