INDEX

Explanations

references to time and historical context

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

WireFormatLite

-0.70

MessageTagHelper

-0.70

setVerticalGroup

-0.69

 newOwner

-0.62

styleType

-0.59

RegressionTest

-0.58

 ListTile

-0.56

ègre

-0.56

 MessageBoxIcon

-0.56

BufferException

-0.55

POSITIVE LOGITS

 past

3.08

past

2.66

Past

2.51

 Past

2.48

 PAST

2.31

 Vergangenheit

2.25

 pasado

2.12

PAST

2.09

 passado

2.03

 passato

1.94

Activations Density 0.310%

references to time and historical context

No Comments

No Known Activations