INDEX

Explanations

occurrences of the letter 't'

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

 myſelf

-1.26

 ſeveral

-1.21

Efq

-1.15

 Reſ

-1.14

 raiſ

-1.12

 themſelves

-1.11

 Diſ

-1.11

 Theſe

-1.10

 Monfieur

-1.09

 ſever

-1.09

POSITIVE LOGITS

1.50

1.25

0.97

ｔ

0.87

0.85

:✨

0.84

0.82

 AssemblyCulture

0.81

0.80

Activations Density 0.108%

occurrences of the letter 't'

No Comments

No Known Activations