INDEX

Explanations

comparative terms denoting degree or intensity

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "much" to emphasize comparisons or intensify statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pta

-0.79

ysc

-0.76

idon

-0.74

esome

-0.74

İĭ

-0.73

emy

-0.73

swick

-0.70

ades

-0.69

ologies

-0.68

yss

-0.67

POSITIVE LOGITS

 appreciated

1.01

 simpler

0.83

ado

0.82

 nicer

0.81

 esteemed

0.78

 admired

0.78

 respected

0.76

NESS

0.76

 enough

0.74

 easier

0.73

Activations Density 0.038%

comparative terms denoting degree or intensity

repeated mentions of the word "much" to emphasize comparisons or intensify statements

No Comments

No Known Activations