INDEX

Explanations

descriptive statements followed by a comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

instances of the word "was" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

achu

-0.67

inite

-0.65

 inhabit

-0.65

arming

-0.62

 affinity

-0.61

ctl

-0.60

gem

-0.60

ennett

-0.59

igrant

-0.59

oper

-0.58

POSITIVE LOGITS

 preceded

1.01

 happening

0.95

wolf

0.86

 followed

0.81

wolves

0.76

 BEFORE

0.75

 done

0.75

 supposed

0.74

 accompanied

0.74

ntil

0.73

Activations Density 0.110%

descriptive statements followed by a comparison or contrast

instances of the word "was" in various contexts

No Comments

No Known Activations