INDEX

Explanations

terms related to causing instability or disruption

oai_token-act-pair · gpt-3.5-turbo

terms related to destabilization and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Rate

-0.73

 Participant

-0.67

elf

-0.67

friend

-0.66

Tree

-0.66

une

-0.65

puted

-0.65

 Origin

-0.64

endi

-0.64

Personal

-0.64

POSITIVE LOGITS

 destabil

1.25

icter

0.92

espie

0.89

izational

0.83

 disarm

0.82

 instability

0.80

ieties

0.78

 Ukrain

0.78

 Rohing

0.78

 psychiat

0.77

Activations Density 0.010%

terms related to causing instability or disruption

terms related to destabilization and its effects

No Comments

No Known Activations