INDEX

Explanations

phrases related to financial institutions like "Wall Street."

oai_token-act-pair · gpt-3.5-turbo

references to "Wall Street."

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

netflix

-0.79

âĶģ

-0.78

ELY

-0.74

çĦ

-0.74

vim

-0.73

cause

-0.71

66666666

-0.70

Â¯Â¯Â¯Â¯

-0.70

sync

-0.70

POSITIVE LOGITS

 Journal

1.07

 firms

1.02

 casino

0.92

 bankers

0.91

 Consulting

0.87

 Banking

0.86

 analysts

0.86

 casinos

0.84

 betting

0.83

 banker

0.83

Activations Density 0.026%

phrases related to financial institutions like "Wall Street."

references to "Wall Street."

No Comments

No Known Activations