INDEX

Explanations

verbs indicating continuation or monitoring of a situation or trend

oai_token-act-pair · gpt-3.5-turbo

conditional phrases expressing hypothetical scenarios

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

ÃįÃį

-0.75

 ILCS

-0.69

Afee

-0.65

 Whitman

-0.64

éĹ

-0.63

ãĥķ

-0.63

aphael

-0.61

senal

-0.61

Sod

-0.59

renheit

-0.58

POSITIVE LOGITS

 sufficiently

0.79

 succeed

0.76

 someday

0.74

 enough

0.74

 succeeds

0.66

 properly

0.64

eret

0.64

 tomorrow

0.63

 correctly

0.62

 fails

0.62

Activations Density 0.612%

verbs indicating continuation or monitoring of a situation or trend

conditional phrases expressing hypothetical scenarios

No Comments

No Known Activations