INDEX

Explanations

references to medical or scientific terms, particularly related to cells

oai_token-act-pair · gpt-3.5-turbo

key terms related to classification and distinctions 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hess

-0.70

reach

-0.61

charg

-0.57

uner

-0.54

 Sinn

-0.53

ml

-0.52

agon

-0.50

 toler

-0.50

 franc

-0.50

yards

-0.48

POSITIVE LOGITS

ï¸ı

0.90

etheless

0.81

²¾

0.72

 guiActive

0.70

IVERS

0.70

Ö¼

0.69

Â¯

0.68

ulhu

0.67

lished

0.67

ularity

0.67

Activations Density 0.362%

references to medical or scientific terms, particularly related to cells

key terms related to classification and distinctions in various contexts

No Comments

No Known Activations