INDEX

Explanations

phrases related to beliefs or perspectives

oai_token-act-pair · gpt-3.5-turbo

phrases related to misleading beliefs or misconceptions

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

 actionGroup

-0.74

phabet

-0.70

ZIP

-0.66

 Miscellaneous

-0.66

 gore

-0.65

illary

-0.64

NCT

-0.61

 collisions

-0.60

NetMessage

-0.60

 Jarvis

-0.59

POSITIVE LOGITS

 assumption

1.44

 belief

1.41

 expectation

1.13

 believing

1.10

 assumptions

1.10

 pessim

1.08

 optimism

1.05

 beliefs

1.05

 impression

1.04

 presumption

1.04

Activations Density 0.972%

phrases related to beliefs or perspectives

phrases related to misleading beliefs or misconceptions

No Comments

No Known Activations