INDEX

Explanations

words related to protection, insulation, and shielding

oai_token-act-pair · gpt-3.5-turbo

terms related to various forms of protection or shielding

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

onde

-0.70

 Kinn

-0.69

orne

-0.66

NC

-0.65

TPP

-0.64

OTA

-0.61

itled

-0.61

acher

-0.60

apest

-0.60

leaf

-0.60

POSITIVE LOGITS

ively

0.87

 protects

0.85

 against

0.83

ously

0.81

ailability

0.80

iveness

0.80

 shielding

0.79

 protecting

0.76

against

0.75

 detection

0.75

Activations Density 0.099%

words related to protection, insulation, and shielding

terms related to various forms of protection or shielding

No Comments

No Known Activations