INDEX

Explanations

references to historical events or time periods, particularly connected to significant years like 17th or 18th century

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

orc

-0.84

enhagen

-0.73

 regenerate

-0.71

ovie

-0.66

 tremend

-0.66

odynamic

-0.65

ensed

-0.65

lication

-0.65

senal

-0.64

mble

-0.64

POSITIVE LOGITS

0.99

0.96

0.94

0.93

rd

0.90

0.89

0.88

0.87

Activations Density 0.036%

references to historical events or time periods, particularly connected to significant years like 17th or 18th century

No Comments

No Known Activations