INDEX

Explanations

occurrences of the word "as" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 purpoſe

-1.02

 houſe

-0.98

 ſtate

-0.97

 ſen

-0.96

 poffe

-0.94

 ſche

-0.89

 raiſ

-0.88

 pleaſure

-0.88

 preſent

-0.88

 neceſſ

-0.88

POSITIVE LOGITS

 LIKE

0.92

 Like

0.90

 like

0.90

LIKE

0.87

UpInside

0.83

Including

0.82

 zoals

0.80

 kuten

0.76

the

0.74

INCLUDING

0.74

Activations Density 0.110%

occurrences of the word "as" in various contexts

No Comments

No Known Activations