INDEX

Explanations

words or phrases followed by "referred to as"

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate alternative names or terms for something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

iem

-0.67

olitics

-0.66

 exploited

-0.65

////////////////////////////////

-0.62

oval

-0.62

eland

-0.62

PLIED

-0.61

 ende

-0.61

reci

-0.60

 stoked

-0.60

POSITIVE LOGITS

enance

0.74

ript

0.72

 phrases

0.68

=\"

0.65

 initials

0.65

å¯

0.65

 pronouns

0.65

acht

0.64

gars

0.64

 them

0.63

Activations Density 0.048%

words or phrases followed by "referred to as"

phrases that indicate alternative names or terms for something

No Comments

No Known Activations