INDEX

Explanations

phrases related to financial forecasting and trends

oai_token-act-pair · gpt-3.5-turbo

phrases related to varying levels of scope or categorization, particularly in the context of duration, classification, or intensity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Haku

-0.70

ä½ľ

-0.67

Į

-0.63

âĸ¬

-0.62

named

-0.62

WAY

-0.61

INST

-0.61

ameless

-0.61

 Mankind

-0.61

Coy

-0.61

POSITIVE LOGITS

 intermediate

0.94

 mids

0.80

mid

0.75

sem

0.74

 semi

0.74

 medium

0.72

jun

0.71

endment

0.70

alli

0.66

rast

0.66

Activations Density 0.293%

phrases related to financial forecasting and trends

phrases related to varying levels of scope or categorization, particularly in the context of duration, classification, or intensity

No Comments

No Known Activations