INDEX

Explanations

references to government or administrative entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

acket

-0.78

thens

-0.72

imum

-0.70

undrum

-0.68

iom

-0.68

hid

-0.67

adobe

-0.67

ylum

-0.66

jon

-0.66

lio

-0.66

POSITIVE LOGITS

 alike

1.56

 perspectives

1.18

 sectors

1.12

 versions

1.09

 viewpoints

1.04

 contexts

1.01

 spheres

0.98

 communities

0.97

 varieties

0.96

 environments

0.95

Activations Density 0.134%

references to government or administrative entities

No Comments

No Known Activations