INDEX

Explanations

words related to sanctuaries or protected areas

oai_token-act-pair · gpt-3.5-turbo

variations of the word "context" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nings

-0.67

zzle

-0.65

hattan

-0.64

 hars

-0.63

NX

-0.62

visors

-0.62

ciation

-0.61

 lockout

-0.61

 diminishing

-0.61

 Cosponsors

-0.61

POSITIVE LOGITS

ãĤ¡

1.00

urn

0.94

acular

0.93

ools

0.92

urnal

0.90

ype

0.88

rine

0.87

ored

0.86

eenth

0.85

rained

0.84

Activations Density 0.041%

words related to sanctuaries or protected areas

variations of the word "context" in various forms

No Comments

No Known Activations