INDEX

Explanations

mentions of death-related topics, including death penalty cases, executions, murder, and mortality

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

Cola

-0.86

CN

-0.75

EEK

-0.74

kef

-0.72

toe

-0.72

CRE

-0.71

umar

-0.69

GB

-0.68

ĸļ

-0.68

oS

-0.66

POSITIVE LOGITS

 procession

0.96

 penalty

0.92

 rites

0.92

 toll

0.92

blow

0.88

guard

0.86

 thro

0.86

adder

0.85

stroke

0.84

 shroud

0.84

Activations Density 0.689%

mentions of death-related topics, including death penalty cases, executions, murder, and mortality

No Comments

No Known Activations