INDEX

Explanations

phrases related to causal relationships

oai_token-act-pair · gpt-3.5-turbo

expressions of necessity or potential impact 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 @ 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

chuk

-0.70

atin

-0.70

gg

-0.70

rike

-0.69

 Legacy

-0.69

ummies

-0.68

alker

-0.67

iors

-0.66

.",

-0.65

cess

-0.65

POSITIVE LOGITS

 incidentally

0.89

Ö¼

0.83

 presumably

0.76

 ironically

0.74

 admittedly

0.69

 coincides

0.68

 hereafter

0.67

?)

0.66

))))

0.66

PK

0.66

Activations Density 0.415%

phrases related to causal relationships

expressions of necessity or potential impact in various contexts

No Comments

No Known Activations