INDEX

Explanations

mentions of the word "Lamb" or "Lambda" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual or character named "Lamb."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

BOOK

-0.68

LIST

-0.67

PLIED

-0.65

ãĥ¯

-0.64

 Kindle

-0.63

 mell

-0.61

ãģ¦

-0.60

 drift

-0.60

 fences

-0.60

 Subtle

-0.59

POSITIVE LOGITS

da

1.15

alle

1.03

onde

1.00

atos

0.98

atin

0.97

asted

0.95

din

0.93

aughs

0.92

adesh

0.91

emouth

0.91

Activations Density 0.041%

mentions of the word "Lamb" or "Lambda" in various contexts

references to a specific individual or character named "Lamb."

No Comments

No Known Activations