INDEX

Explanations

references to "Ta," indicating a focus on characters or entities with that name or prefix

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

</h1>

-0.73

 Lowry

-0.73

 Miller

-0.72

 Klein

-0.67

 Cline

-0.66

ции

-0.66

-0.65

thom

-0.65

 Schlegel

-0.61

 Lawson

-0.61

POSITIVE LOGITS

Ta

1.85

Ta

1.79

ta

1.63

ta

1.57

TA

1.52

TA

1.46

 Taft

1.39

 Tape

1.25

Tape

1.23

TAP

1.20

Activations Density 0.114%

references to "Ta," indicating a focus on characters or entities with that name or prefix

No Comments

No Known Activations