INDEX

Explanations

organizations and terms related to specific events or themes, particularly those associated with negative actions or controversy

oai_token-act-pair · gpt-3.5-turbo

references to the color red

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

SPONSORED

-0.80

Â·Â·

-0.74

Scroll

-0.67

ISTORY

-0.66

-0.65

oteric

-0.65

Story

-0.64

BIL

-0.63

hang

-0.62

ZI

-0.61

POSITIVE LOGITS

uced

1.15

uces

1.07

ucing

1.03

ding

1.03

der

0.99

irect

0.98

acted

0.97

emption

0.97

ragon

0.95

eem

0.94

Activations Density 0.016%

organizations and terms related to specific events or themes, particularly those associated with negative actions or controversy

references to the color red

No Comments

No Known Activations