INDEX

Explanations

words related to progression, reaching a target, and achieving a goal

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soType

-0.83

oral

-0.69

 sponsoring

-0.62

irection

-0.60

 fostering

-0.59

voice

-0.58

 advocacy

-0.58

 Supporting

-0.57

 prescribing

-0.57

chool

-0.57

POSITIVE LOGITS

 exhausted

1.00

Completed

0.99

 finish

0.99

 finished

0.98

 succeeded

0.94

 exhaustion

0.92

 completes

0.90

 succeed

0.90

 completed

0.90

 missed

0.88

Activations Density 0.448%

words related to progression, reaching a target, and achieving a goal

No Comments

No Known Activations