INDEX

Explanations

mentions of locations or entities followed by the word "state."

oai_token-act-pair · gpt-3.5-turbo

references to "state" 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

poons

-0.88

Maw

-0.82

edin

-0.73

sites

-0.73

ellery

-0.71

ghazi

-0.70

eatures

-0.68

 Planes

-0.68

isition

-0.67

 Aires

-0.66

POSITIVE LOGITS

wide

1.07

 legislature

1.05

 legislatures

1.05

 Legislature

0.97

 legislators

0.91

 senator

0.87

 senate

0.86

 trooper

0.86

 troopers

0.85

 lawmakers

0.83

Activations Density 0.063%

mentions of locations or entities followed by the word "state."

references to "state" in various contexts

No Comments

No Known Activations