INDEX

Explanations

pronouns referring to people

oai_token-act-pair · gpt-3.5-turbo

references to individuals or groups in the context of struggles or issues

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

 Eleven

-0.70

CCC

-0.68

Rating

-0.59

Offline

-0.58

 Binding

-0.58

 Witt

-0.58

 Links

-0.58

stellar

-0.58

 Sequ

-0.58

 Dome

-0.57

POSITIVE LOGITS

're

1.70

've

1.33

are

1.24

 themselves

1.21

'll

1.21

 deserve

1.12

 aren

1.11

 were

1.08

 perceive

1.07

'd

1.06

Activations Density 0.240%

pronouns referring to people

references to individuals or groups in the context of struggles or issues

No Comments

No Known Activations