INDEX

Explanations

proper nouns related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific geographical locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

mble

-0.71

uminati

-0.70

sych

-0.61

sembly

-0.60

ession

-0.59

 Clair

-0.57

ointed

-0.57

 Mehran

-0.56

nz

-0.56

wagen

-0.55

POSITIVE LOGITS

 itself

0.98

's

0.85

selves

0.81

âĢ²

0.73

 Himself

0.71

ipedia

0.69

 himself

0.68

 territory

0.67

 herself

0.66

 proper

0.65

Activations Density 0.390%

proper nouns related to geographical locations

specific geographical locations and entities

No Comments

No Known Activations