INDEX

Explanations

mentions of specific locations or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of common prepositions and conjunctions

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

Buk

-0.76

 Mate

-0.76

 cutter

-0.70

 Wake

-0.69

 Commands

-0.67

Hug

-0.66

Wad

-0.65

 Hear

-0.65

 Knot

-0.63

 challeng

-0.63

POSITIVE LOGITS

terday

0.95

redients

0.91

ilogy

0.89

selves

0.85

soDeliveryDate

0.84

theless

0.83

psons

0.80

:(

0.80

acters

0.79

have

0.78

Activations Density 0.377%

mentions of specific locations or events

occurrences of common prepositions and conjunctions

No Comments

No Known Activations