INDEX

Explanations

instances where the phrase "no stranger" is used

oai_token-act-pair · gpt-3.5-turbo

the phrase "no stranger" 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

RAFT

-0.74

mosp

-0.72

romy

-0.70

gary

-0.68

rex

-0.64

 Comes

-0.62

ribe

-0.61

roxy

-0.60

endar

-0.59

essor

-0.59

POSITIVE LOGITS

xious

1.19

 longer

1.00

 matter

0.93

except

0.92

 conceivable

0.86

 doubt

0.85

 indication

0.81

obs

0.79

onday

0.77

oooooooo

0.76

Activations Density 0.058%

instances where the phrase "no stranger" is used

the phrase "no stranger" in various contexts

No Comments

No Known Activations