INDEX

Explanations

pronouns followed by verbs or possessive pronouns

oai_token-act-pair · gpt-3.5-turbo

references to monetary transactions and financial obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contrasting

-0.65

 imitation

-0.61

Pattern

-0.60

 resemblance

-0.59

clusions

-0.59

 parallels

-0.59

Hug

-0.59

rossover

-0.58

ruary

-0.57

 Dating

-0.57

POSITIVE LOGITS

 expended

1.01

 allotted

1.01

 expend

0.97

 accrued

0.95

 earn

0.93

 earns

0.93

 allot

0.92

 allocate

0.92

 earned

0.88

 spend

0.88

Activations Density 0.124%

pronouns followed by verbs or possessive pronouns

references to monetary transactions and financial obligations

No Comments

No Known Activations