INDEX

Explanations

references to technological terms or proper nouns related to technology

oai_token-act-pair · gpt-3.5-turbo

specific product or brand names related to technology and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

.</

-0.82

.).

-0.82

.''

-0.78

.ï¿½

-0.77

,...

-0.77

.<

-0.77

]."

-0.76

 ..."

-0.72

}.

-0.67

''.

-0.65

POSITIVE LOGITS

rul

0.68

ibliography

0.61

 Facts

0.60

 Canaver

0.59

ctive

0.55

':

0.55

 Variant

0.55

 Profile

0.54

gard

0.54

ahime

0.54

Activations Density 1.429%

references to technological terms or proper nouns related to technology

specific product or brand names related to technology and media

No Comments

No Known Activations