INDEX

Explanations

detailed information related to a specific topic within longer texts

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

ATES

-0.70

olyn

-0.67

hetto

-0.67

ERROR

-0.66

omp

-0.63

 Scand

-0.61

OURCE

-0.61

ereo

-0.60

ces

-0.60

YP

-0.59

POSITIVE LOGITS

ivity

1.26

matter

1.21

ivist

1.18

ively

1.17

ivities

1.16

ivism

1.05

itatively

1.04

icals

0.98

ion

0.98

ivation

0.98

Activations Density 0.165%

detailed information related to a specific topic within longer texts

No Comments

No Known Activations