INDEX

Explanations

questions, particularly those regarding uncertainty or decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

AddTagHelper

-0.92

 stället

-0.79

 télécharge

-0.75

 Alternative

-0.74

 فريبيس

-0.71

 Functional

-0.71

 Practical

-0.70

########.

-0.70

 Pergamon

-0.69

 pioggia

-0.69

POSITIVE LOGITS

po

0.61

0.56

But

0.55

0.53

Br

0.52

0.50

0.48

Wow

0.47

Do

0.47

Activations Density 0.735%

questions, particularly those regarding uncertainty or decision-making

No Comments

No Known Activations