INDEX

Explanations

phrases related to detailed descriptions of past events or actions

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

cation

-0.86

terness

-0.79

uncture

-0.78

iliation

-0.77

icism

-0.75

atform

-0.74

fecture

-0.72

position

-0.72

heit

-0.72

mire

-0.72

POSITIVE LOGITS

 kinds

1.10

 sorts

1.05

 facts

1.04

 truths

1.04

 types

0.99

types

0.96

 days

0.94

 cases

0.94

 qualities

0.93

 fellows

0.92

Activations Density 2.690%

phrases related to detailed descriptions of past events or actions

No Comments

No Known Activations