INDEX

Explanations

comparative adjectives expressing increasing intensity

oai_token-act-pair · gpt-3.5-turbo

the word "even" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rend

-0.77

asus

-0.69

ection

-0.66

ected

-0.65

iliate

-0.64

HCR

-0.63

aim

-0.61

olitics

-0.61

isal

-0.61

raints

-0.60

POSITIVE LOGITS

handed

1.01

 remotely

0.77

handedly

0.76

 though

0.74

romeda

0.72

NESS

0.71

 craz

0.70

 stricter

0.67

 MORE

0.67

ivari

0.67

Activations Density 0.051%

comparative adjectives expressing increasing intensity

the word "even" in various contexts

No Comments

No Known Activations