INDEX

Explanations

influential proper nouns followed by an action or a description

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "of"

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

respective

-0.71

 collateral

-0.69

accompan

-0.69

 categor

-0.67

required

-0.66

userc

-0.64

 relate

-0.64

 accordingly

-0.62

 modifiers

-0.62

 placeholder

-0.62

POSITIVE LOGITS

 Bellev

0.95

 Alexandria

0.92

 Omaha

0.90

 Georgetown

0.90

 Syracuse

0.87

 Providence

0.84

icial

0.83

 Anaheim

0.82

 Hartford

0.82

 Salt

0.80

Activations Density 0.067%

influential proper nouns followed by an action or a description

occurrences of the word "of"

No Comments

No Known Activations