INDEX

Explanations

terms related to immune response and inflammatory processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Manor

-0.79

Arcade

-0.76

 Grounds

-0.76

Rules

-0.75

aughs

-0.75

 gems

-0.74

Beast

-0.73

geist

-0.73

 Purg

-0.72

 sensibilities

-0.70

POSITIVE LOGITS

zyme

1.03

 Aden

1.02

activation

1.01

emia

1.01

cyt

0.99

ox

0.99

igen

0.99

âĢĲ

0.99

 inhibition

0.98

oxicity

0.98

Activations Density 0.488%

terms related to immune response and inflammatory processes

No Comments

No Known Activations