INDEX

Explanations

mentions of holding individuals or entities responsible or accountable for their actions

oai_token-act-pair · gpt-3.5-turbo

references to accountability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

ker

-0.85

yip

-0.76

othe

-0.76

colo

-0.73

nz

-0.70

ijn

-0.70

ften

-0.70

lyn

-0.70

ning

-0.70

::::::::

-0.70

POSITIVE LOGITS

 accountable

0.94

rity

0.92

 Accountability

0.86

 accountability

0.79

 adjud

0.74

 Skydragon

0.71

 Disclosure

0.68

IBLE

0.68

displayText

0.67

 institution

0.67

Activations Density 0.017%

mentions of holding individuals or entities responsible or accountable for their actions

references to accountability in various contexts

No Comments

No Known Activations