INDEX

Explanations

technical jargon and terms related to evaluation and assessment

oai_token-act-pair · gpt-3.5-turbo

references to tests, evaluations, or assessments, particularly in a comparative or scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ô

-0.89

 Latest

-0.72

.:

-0.67

 Last

-0.67

 GOODMAN

-0.67

 Marketable

-0.66

},{"

-0.65

igmatic

-0.65

actionDate

-0.65

.#

-0.65

POSITIVE LOGITS

 lacked

1.71

 remained

1.36

 tended

1.34

 wasn

1.28

 hadn

1.28

 resembled

1.28

 didn

1.27

 seemed

1.26

 consisted

1.24

did

1.21

Activations Density 0.527%

technical jargon and terms related to evaluation and assessment

references to tests, evaluations, or assessments, particularly in a comparative or scientific context

No Comments

No Known Activations