INDEX

Explanations

references to 'mid' or 'mid-year' time indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sucesor

-0.83

sme

-0.83

 uVar

-0.81

ので

-0.80

 חיצוניים

-0.78

parentElement

-0.78

ReusableCell

-0.77

**)

-0.76

Yourself

-0.72

 Templ

-0.71

POSITIVE LOGITS

 midwives

1.02

 Bids

0.99

 midwife

0.97

BID

0.97

mid

0.96

 Bidding

0.96

Bid

0.95

MID

0.94

 bids

0.92

 Biden

0.92

Activations Density 0.235%

references to 'mid' or 'mid-year' time indicators

No Comments

No Known Activations