INDEX

Explanations

specific alphanumeric identifiers or codes associated with online content, particularly related to media or URLs

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

 pleaſure

-0.99

 myſelf

-0.96

 ſtate

-0.95

 Reſ

-0.93

ſelf

-0.92

Eſ

-0.92

ſelves

-0.92

 themſelves

-0.91

 houſe

-0.89

PhysRevD

-0.88

POSITIVE LOGITS

0.83

0.80

↵↵

0.77

0.75

0.69

0.68

0.67

0.66

Activations Density 0.074%

specific alphanumeric identifiers or codes associated with online content, particularly related to media or URLs

No Comments

No Known Activations