INDEX

Explanations

words related to combat, battles, or strong confrontations

oai_token-act-pair · gpt-3.5-turbo

elements related to significant emotional events or actions

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

escription

-0.67

ationally

-0.64

govtrack

-0.61

itimate

-0.61

-+-+

-0.61

:[

-0.59

inarily

-0.59

catentry

-0.59

).[

-0.58

 authorised

-0.57

POSITIVE LOGITS

gling

0.70

Magikarp

0.63

 hats

0.56

 cows

0.56

 overshadow

0.55

 roses

0.55

 lettuce

0.54

 Shant

0.54

usra

0.54

 rejoice

0.54

Activations Density 1.251%

words related to combat, battles, or strong confrontations

elements related to significant emotional events or actions

No Comments

No Known Activations