INDEX

Explanations

verbs related to threatening actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating threats or aggressive actions

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

 Parables

-0.77

 guiName

-0.67

CTV

-0.66

Display

-0.65

oret

-0.65

ellen

-0.63

worn

-0.62

 Bought

-0.62

 Videos

-0.61

 incorporated

-0.60

POSITIVE LOGITS

 retaliation

1.03

 retribution

0.99

 repr

0.84

 retaliate

0.82

 boycott

0.78

 harming

0.77

 eviction

0.74

 annihilation

0.74

 intimidation

0.73

 wrath

0.73

Activations Density 0.104%

verbs related to threatening actions

phrases indicating threats or aggressive actions

No Comments

No Known Activations