INDEX

Explanations

verbs related to actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

action verbs and their usage in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

berus

-0.75

Applic

-0.74

fired

-0.72

winner

-0.71

struction

-0.68

apo

-0.68

éĹ

-0.66

affer

-0.65

shut

-0.65

pletion

-0.63

POSITIVE LOGITS

 themselves

1.13

 differently

0.97

 theirs

0.95

 their

0.92

 THEIR

0.84

 alike

0.80

 instinctively

0.76

 endlessly

0.74

 freely

0.73

ingly

0.69

Activations Density 0.523%

verbs related to actions or behaviors

action verbs and their usage in context

No Comments

No Known Activations