INDEX

Explanations

verbs related to actions that have an impact on society or the economy

oai_token-act-pair · gpt-3.5-turbo

actions or processes that indicate improvement or enhancement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocene

-0.72

rell

-0.67

Oo

-0.65

raid

-0.65

 helicop

-0.64

rika

-0.62

blank

-0.62

tree

-0.61

 prow

-0.61

psons

-0.60

POSITIVE LOGITS

 alike

0.92

 accordingly

0.77

 consequently

0.71

 them

0.68

 consequ

0.63

 thereafter

0.62

 others

0.62

 thereby

0.60

angering

0.60

 countless

0.58

Activations Density 0.287%

verbs related to actions that have an impact on society or the economy

actions or processes that indicate improvement or enhancement in various contexts

No Comments

No Known Activations