INDEX

Explanations

references to specific political figures and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Figure

-0.53

 okay

-0.52

",

-0.50

”,

-0.49

]",

-0.48

 Reverend

-0.47

".

-0.47

”.

-0.47

argli

-0.46

________________

-0.46

POSITIVE LOGITS

Oct

1.22

Fig

1.21

 Sept

1.19

Aug

1.17

Fig

1.16

Gov

1.14

Feb

1.11

Nov

1.10

 Figs

1.05

FIG

1.04

Activations Density 0.775%

references to specific political figures and locations

No Comments

No Known Activations