INDEX

Explanations

instances where an action occurred as a result of certain circumstances

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of "a" or equivalent indefinite articles 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 @ 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

âĿ

-0.83

alties

-0.72

andon

-0.72

events

-0.71

mares

-0.70

ashtra

-0.69

pages

-0.69

DOM

-0.67

Dutch

-0.67

EMA

-0.67

POSITIVE LOGITS

 result

1.17

 reminder

1.00

 standalone

0.97

 consequence

0.95

 spectator

0.91

 backdrop

0.91

 precaution

0.88

 precursor

0.87

 prerequisite

0.87

 catalyst

0.87

Activations Density 0.098%

instances where an action occurred as a result of certain circumstances

phrases emphasizing the concept of "a" or equivalent indefinite articles in various contexts

No Comments

No Known Activations