INDEX

Explanations

concepts related to impossibility or unfeasibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.68

<eos>

-0.66

↵↵

-0.65

-0.64

↵

-0.64

-0.61

en

-0.58

er

-0.57

POSITIVE LOGITS

 Anſ

1.25

 Theſe

1.24

 Northwest

1.13

ConstraintMaker

1.12

TagHelper

1.09

 whoſe

1.08

 myſelf

1.08

Northwest

1.08

Efq

1.08

 Houſe

1.07

Activations Density 0.123%

concepts related to impossibility or unfeasibility

No Comments

No Known Activations