INDEX

Explanations

words related to "and."

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 tremend

-0.84

keley

-0.71

odcast

-0.70

mpeg

-0.69

kefeller

-0.68

lectic

-0.67

AMS

-0.65

«ĺ

-0.65

 WARN

-0.61

¥µ

-0.61

POSITIVE LOGITS

idate

0.96

rogen

0.90

romeda

0.90

rost

0.89

rew

0.88

hra

0.87

rogens

0.85

amide

0.83

inav

0.80

erers

0.80

Activations Density 0.029%

words related to "and."

the conjunction "and" used in various contexts

No Comments

No Known Activations