INDEX

Explanations

statements that emphasize and point out specific information or situations

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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 @ 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

emis

-0.80

YS

-0.70

oby

-0.69

LIN

-0.66

IVERS

-0.66

Tax

-0.66

tones

-0.64

thro

-0.64

hips

-0.64

apolis

-0.64

POSITIVE LOGITS

 includes

0.89

 culminated

0.86

 translates

0.85

 pesky

0.82

 contradicts

0.81

 resulted

0.80

 mattered

0.79

cher

0.79

 leads

0.76

 amounted

0.75

Activations Density 0.112%

statements that emphasize and point out specific information or situations

the word "that" in various contexts

No Comments

No Known Activations