INDEX

Explanations

phrases related to ethical issues or challenges that require action

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

etheless

-0.88

swer

-0.76

 endeav

-0.73

icter

-0.73

 nutshell

-0.72

 undet

-0.71

 indu

-0.69

 dictated

-0.68

ibrary

-0.67

lamm

-0.66

POSITIVE LOGITS

Indeed

1.25

Asked

1.19

Newsletter

1.19

Adds

1.14

Another

1.12

Refer

1.10

Others

1.10

Said

1.08

Mos

1.04

Still

1.02

Activations Density 1.000%

phrases related to ethical issues or challenges that require action

No Comments

No Known Activations