INDEX

Explanations

pronouns and possessive nouns

oai_token-act-pair · gpt-3.5-turbo

references to possession or ownership

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

eers

-0.82

netflix

-0.82

river

-0.77

 Frazier

-0.76

hari

-0.72

ahead

-0.72

haus

-0.72

 Uriel

-0.71

Tree

-0.70

ingle

-0.69

POSITIVE LOGITS

own

1.68

 newfound

1.16

 inability

1.15

 predicament

1.14

 intentions

1.13

 actions

1.07

 plight

1.06

 impending

1.06

 dealings

1.05

 predecessors

1.03

Activations Density 0.376%

pronouns and possessive nouns

references to possession or ownership

No Comments

No Known Activations