INDEX

Explanations

phrases related to reasons or causes

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causes or reasons behind various outcomes or phenomena

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Å¡

-0.82

İĭ

-0.79

atomic

-0.72

 Tomorrow

-0.67

cffff

-0.67

cknow

-0.66

ĺ

-0.65

 ACPI

-0.65

sleep

-0.65

ãĥĪ

-0.64

POSITIVE LOGITS

 Catalyst

0.69

ulla

0.67

 earners

0.64

liest

0.63

\">

0.63

 exerc

0.63

ainer

0.62

 tackled

0.61

":["

0.61

 deposits

0.61

Activations Density 0.243%

phrases related to reasons or causes

phrases that indicate causes or reasons behind various outcomes or phenomena

No Comments

No Known Activations