INDEX

Explanations

the word "than" in various contexts, indicating comparisons or measurements

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

quantitative comparisons using the word "than"

oai_token-act-pair · gpt-3.5-turbo

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

ilic

-0.74

ãĤ¼ãĤ¦ãĤ¹

-0.73

NEY

-0.68

 Bomber

-0.67

 derog

-0.66

oris

-0.65

EMENT

-0.64

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.62

ãĤ¿

-0.62

OSP

-0.62

POSITIVE LOGITS

whelming

0.87

perties

0.75

capacity

0.70

0.69

represent

0.67

fif

0.65

 tripled

0.65

 half

0.65

usercontent

0.64

vernment

0.63

Activations Density 0.068%

the word "than" in various contexts, indicating comparisons or measurements

quantitative comparisons using the word "than"

No Comments

No Known Activations