INDEX

Explanations

pronouns and verbs indicating personal experience or involvement

oai_token-act-pair · gpt-3.5-turbo

references to personal experiences and struggles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 nods

-0.77

endment

-0.76

 trustworthy

-0.67

Awesome

-0.66

$$$$

-0.66

ops

-0.65

 clicks

-0.65

enary

-0.64

independent

-0.64

 Guinness

-0.64

POSITIVE LOGITS

 faced

1.28

 encountered

1.18

 endured

1.15

 incurred

1.12

 inflict

1.07

 inflicted

1.06

 encounter

1.06

 caused

1.06

 suffered

1.04

 suffer

1.04

Activations Density 0.193%

pronouns and verbs indicating personal experience or involvement

references to personal experiences and struggles

No Comments

No Known Activations