INDEX

Explanations

words related to directions or destinations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "go" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hold

-0.65

squ

-0.62

aire

-0.61

 Horus

-0.60

scl

-0.59

ateurs

-0.58

ablo

-0.57

 inhab

-0.57

Naz

-0.57

 resembled

-0.56

POSITIVE LOGITS

etting

0.84

ggle

0.75

lems

0.74

 anyway

0.73

!/

0.73

 downhill

0.73

 unnoticed

0.72

 anyways

0.71

 viral

0.70

finding

0.67

Activations Density 0.047%

words related to directions or destinations

instances of the word "go" in various contexts

No Comments

No Known Activations