INDEX

Explanations

concepts related to personal responsibility and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.00

 itſelf

-0.97

 Monfieur

-0.89

."));

-0.88

 themſelves

-0.87

Efq

-0.86

 himſelf

-0.83

 ſeveral

-0.83

 Jefus

-0.82

ſelves

-0.81

POSITIVE LOGITS

 chances

0.77

 Chances

0.73

Chances

0.67

Imagine

0.59

If

0.58

 then

0.57

 odds

0.55

 unless

0.54

 guess

0.54

Or

0.53

Activations Density 0.300%

concepts related to personal responsibility and accountability

No Comments

No Known Activations