INDEX

Explanations

terms related to accomplishments and achievements

oai_token-act-pair · gpt-3.5-turbo

mentions of achievements and accomplishments

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

©¶æ

-0.77

creen

-0.74

ondo

-0.70

odynamic

-0.69

trop

-0.67

ocard

-0.64

asus

-0.63

osate

-0.63

otin

-0.61

ENA

-0.61

POSITIVE LOGITS

 accomplishment

1.11

 achievement

1.05

 accomplished

1.03

 achievements

1.03

ments

1.02

 feats

1.01

 accomplishments

0.98

 attainment

0.96

ment

0.93

 achie

0.93

Activations Density 0.046%

terms related to accomplishments and achievements

mentions of achievements and accomplishments

No Comments

No Known Activations