INDEX

Explanations

phrases related to rationale or reasoning for certain actions or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to explanations and justifications for actions or beliefs

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

semble

-0.88

redd

-0.75

oner

-0.69

chance

-0.69

rop

-0.67

zig

-0.66

plet

-0.65

hold

-0.65

chin

-0.65

omez

-0.65

POSITIVE LOGITS

 rationale

1.13

why

1.02

 justification

0.96

SourceFile

0.93

 justifying

0.92

 reasoning

0.87

 behind

0.86

WHY

0.84

 underpin

0.78

 justify

0.78

Activations Density 0.025%

phrases related to rationale or reasoning for certain actions or decisions

terms related to explanations and justifications for actions or beliefs

No Comments

No Known Activations