INDEX

Explanations

comparisons of varying degrees between two entities or actions

oai_token-act-pair · gpt-3.5-turbo

expressions of intensity or degree in sentiments

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

loe

-0.68

 Nadu

-0.67

 Reincarnated

-0.65

 Sorceress

-0.65

Tir

-0.64

utenberg

-0.61

gged

-0.60

PLIED

-0.60

hetical

-0.59

 privilege

-0.58

POSITIVE LOGITS

etheless

0.94

ernaut

0.73

rays

0.72

appropriately

0.71

©¶æ

0.71

ciating

0.69

é£

0.69

 veter

0.69

Ø¯

0.66

ever

0.65

Activations Density 0.641%

comparisons of varying degrees between two entities or actions

expressions of intensity or degree in sentiments

No Comments

No Known Activations