INDEX

Explanations

words related to storytelling and personal anecdotes

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

WARD

-0.66

FORMATION

-0.65

PORT

-0.65

 lockout

-0.65

ences

-0.64

 Civic

-0.64

 constrained

-0.63

 visitation

-0.63

ENCE

-0.62

gaard

-0.61

POSITIVE LOGITS

amps

1.19

icago

1.19

owder

1.19

akra

1.16

ampion

1.14

ieft

1.13

orus

1.13

ampions

1.13

isel

1.13

ivalry

1.13

Activations Density 0.459%

words related to storytelling and personal anecdotes

No Comments

No Known Activations