INDEX

Explanations

verbs relating to accomplishing or reaching a goal

oai_token-act-pair · gpt-3.5-turbo

references to the concept of achieving goals or objectives

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

cloth

-0.68

otta

-0.67

seed

-0.65

RNA

-0.63

©¶æ

-0.63

sbm

-0.62

osate

-0.61

letter

-0.61

 scanned

-0.60

 Frie

-0.60

POSITIVE LOGITS

 attainment

0.92

 mastery

0.89

ments

0.84

 greatness

0.83

 fruition

0.82

iage

0.82

 achievement

0.81

 accomplish

0.81

chieve

0.80

 parity

0.80

Activations Density 0.039%

verbs relating to accomplishing or reaching a goal

references to the concept of achieving goals or objectives

No Comments

No Known Activations