INDEX

Explanations

phrases related to accountability and responsibility

oai_token-act-pair · gpt-3.5-turbo

instances of temporal phrases or references to time

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assad

-0.80

ascus

-0.74

interpret

-0.69

 ..."

-0.68

hig

-0.64

 whats

-0.62

intern

-0.60

Rated

-0.60

DES

-0.59

operator

-0.59

POSITIVE LOGITS

 starters

0.63

 grep

0.61

sofar

0.59

inarily

0.59

 Firstly

0.58

 Starr

0.57

 Suppose

0.56

ensibly

0.56

itialized

0.55

asma

0.54

Activations Density 0.658%

phrases related to accountability and responsibility

instances of temporal phrases or references to time

No Comments

No Known Activations