INDEX

Explanations

phrases related to taking action or making progress

oai_token-act-pair · gpt-3.5-turbo

phrases involving actions or processes that involve "taking steps" towards a specific goal or outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Cum

-0.75

 Syndrome

-0.70

 Nightmares

-0.70

 Faul

-0.69

 Phill

-0.69

 Cros

-0.69

 syndrome

-0.67

 flashes

-0.67

 Dise

-0.66

ivas

-0.65

POSITIVE LOGITS

 resolve

1.01

 improve

0.95

 ensure

0.92

 achieve

0.90

 prevent

0.90

 accomplish

0.90

 resolving

0.86

 safeguard

0.85

 thwart

0.85

 reverse

0.84

Activations Density 0.123%

phrases related to taking action or making progress

phrases involving actions or processes that involve "taking steps" towards a specific goal or outcome

No Comments

No Known Activations