INDEX

Explanations

words related to a specific country

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "IA" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

found

-0.69

 shifting

-0.68

 claws

-0.68

 paws

-0.67

 entr

-0.66

 refreshing

-0.66

Â¨

-0.65

 Devil

-0.64

 mates

-0.64

 reck

-0.63

POSITIVE LOGITS

IA

4.24

IAS

1.96

IAN

1.88

ia

1.84

IDA

1.69

IUM

1.59

ICA

1.50

ILA

1.48

IE

1.48

IO

1.47

Activations Density 0.008%

words related to a specific country

mentions of the term "IA" and its variations

No Comments

No Known Activations