INDEX

Explanations

desert-related terms

oai_token-act-pair · gpt-3.5-turbo

references to desert environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inventoryQuantity

-0.94

soType

-0.82

OPA

-0.81

OA

-0.81

Reviewer

-0.77

yright

-0.71

enny

-0.69

nder

-0.69

aryn

-0.67

ACA

-0.66

POSITIVE LOGITS

 sands

0.96

ification

0.92

 Desert

0.84

 desert

0.83

 tort

0.83

ashtra

0.79

 wasteland

0.78

urous

0.77

 dwell

0.76

 canyon

0.74

Activations Density 0.025%

desert-related terms

references to desert environments

No Comments

No Known Activations