INDEX

Explanations

phrases related to taking action or making decisions

oai_token-act-pair · gpt-3.5-turbo

words relating to a form of suffix or verb conjugation, particularly those ending in "ed" or "ing."

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

intosh

-0.79

 WATCHED

-0.73

istan

-0.69

perty

-0.69

Products

-0.67

anni

-0.66

akespe

-0.66

akia

-0.65

ylum

-0.65

framework

-0.61

POSITIVE LOGITS

eding

0.93

ication

0.82

uctor

0.80

irect

0.76

eded

0.75

vironment

0.70

uces

0.70

uce

0.69

velop

0.69

uced

0.68

Activations Density 0.019%

phrases related to taking action or making decisions

words relating to a form of suffix or verb conjugation, particularly those ending in "ed" or "ing."

No Comments

No Known Activations