INDEX

Explanations

phrases or identifiers related to specific sections or headings in a text

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

natureconservancy

-0.68

ãĤ·ãĥ£

-0.67

fitting

-0.67

mission

-0.66

urnal

-0.66

kers

-0.64

nces

-0.64

hered

-0.63

notice

-0.62

ches

-0.62

POSITIVE LOGITS

AND

1.04

ARD

0.98

ILL

0.89

ERSON

0.86

IENT

0.84

IDE

0.83

AL

0.83

RAG

0.83

LESS

0.83

ING

0.82

Activations Density 0.009%

phrases or identifiers related to specific sections or headings in a text

the conjunction "and" used in various contexts

No Comments

No Known Activations