INDEX

Explanations

instances where the phrase "go ahead" is used

oai_token-act-pair · gpt-3.5-turbo

usage of the phrase "go ahead."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

mini

-0.72

cu

-0.72

odor

-0.71

cci

-0.69

urus

-0.68

brid

-0.68

RAW

-0.68

rival

-0.68

OSS

-0.66

Case

-0.66

POSITIVE LOGITS

olicy

0.79

erk

0.77

 unnoticed

0.76

 reproduce

0.76

 blindly

0.73

 undet

0.72

acht

0.68

 autop

0.68

 rename

0.68

 anyway

0.68

Activations Density 0.011%

instances where the phrase "go ahead" is used

usage of the phrase "go ahead."

No Comments

No Known Activations