INDEX

Explanations

words related to counterpoints or contrasting views followed by a strong stance or argument

oai_token-act-pair · gpt-3.5-turbo

the end of text tokens

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agra

-0.76

itto

-0.69

kie

-0.64

oufl

-0.64

chnology

-0.60

analysis

-0.60

 vein

-0.59

idon

-0.59

tnc

-0.59

rongh

-0.58

POSITIVE LOGITS

tons

1.09

 nevertheless

0.88

 alas

0.87

 nonetheless

0.87

chery

0.84

 fortunately

0.79

chers

0.74

 luckily

0.73

hey

0.69

GHC

0.68

Activations Density 0.099%

words related to counterpoints or contrasting views followed by a strong stance or argument

the end of text tokens

No Comments

No Known Activations