INDEX

Explanations

names or references related to "Cox"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Cox."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aiden

-0.71

 contagious

-0.70

phasis

-0.69

LEASE

-0.65

juven

-0.64

 psychiat

-0.63

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.63

 autos

-0.63

akin

-0.61

 lockout

-0.60

POSITIVE LOGITS

Cox

0.93

icut

0.93

boro

0.93

ulla

0.90

elia

0.89

nown

0.88

dot

0.86

erton

0.86

sey

0.86

son

0.83

Activations Density 0.018%

names or references related to "Cox"

references to the name "Cox."

No Comments

No Known Activations