INDEX

Explanations

financial and data-centric terms like "analysis," "budget," and "tax cuts."

oai_token-act-pair · gpt-3.5-turbo

analytical terms and phrases related to reporting or commentary

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ances

-0.87

raz

-0.75

ages

-0.73

rolog

-0.68

seller

-0.68

aged

-0.66

rolled

-0.62

ulum

-0.62

emaker

-0.61

eded

-0.61

POSITIVE LOGITS

Analysis

1.29

 Interpret

0.80

livious

0.76

uador

0.75

 Weak

0.73

notations

0.70

 Insight

0.70

 Analysis

0.70

 Scan

0.70

imbabwe

0.69

Activations Density 0.013%

financial and data-centric terms like "analysis," "budget," and "tax cuts."

analytical terms and phrases related to reporting or commentary

No Known Activations