INDEX

Explanations

phrases related to the UFC (Ultimate Fighting Championship) events

oai_token-act-pair · gpt-3.5-turbo

references to UFC events or related terminology

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

izabeth

-0.76

matter

-0.76

ebted

-0.69

DOE

-0.69

 MacArthur

-0.67

capacity

-0.67

 Pelosi

-0.66

anyahu

-0.65

istics

-0.64

 Helpful

-0.64

POSITIVE LOGITS

UFC

0.89

 Tournament

0.85

 Fight

0.83

Fighting

0.79

PDATE

0.76

 heavyweight

0.76

PA

0.75

 Tonight

0.74

 Wrest

0.73

 Playoffs

0.73

Activations Density 0.015%

phrases related to the UFC (Ultimate Fighting Championship) events

references to UFC events or related terminology

No Comments

No Known Activations