INDEX

Explanations

mentions of the name "James"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "James" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

cert

-0.74

sites

-0.70

ģ«

-0.69

ĻĤ

-0.69

ajo

-0.68

employment

-0.67

ĺħ

-0.66

 administr

-0.64

notations

-0.64

 correct

-0.64

POSITIVE LOGITS

 Harden

0.94

 Madison

0.92

 Roberts

0.91

 Potter

0.90

 Holmes

0.90

 Webb

0.87

 Joyce

0.85

 Franco

0.85

 Beard

0.84

 Cameron

0.82

Activations Density 0.010%

mentions of the name "James"

mentions of the name "James" in various contexts

No Comments

No Known Activations