INDEX

Explanations

words related to disagreement, disapproval, and dismantling

oai_token-act-pair · gpt-3.5-turbo

words that begin with "dis" indicating negative connotations or concepts

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

 Suit

-0.77

 Juliet

-0.76

 Shogun

-0.66

OPLE

-0.66

 Pose

-0.65

 sinks

-0.65

 Goth

-0.64

 Flow

-0.63

 Opportun

-0.61

terday

-0.61

POSITIVE LOGITS

rup

1.26

ordered

1.18

array

1.16

burse

1.16

section

1.15

quiet

1.14

qus

1.13

assemb

1.12

organized

1.11

aff

1.11

Activations Density 0.012%

words related to disagreement, disapproval, and dismantling

words that begin with "dis" indicating negative connotations or concepts

No Comments

No Known Activations