INDEX

Explanations

this neuron is looking for instances where something is almost but not entirely fitting or meeting expectations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating uncertainty or hesitation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

olan

-0.84

uments

-0.82

selage

-0.73

cius

-0.72

 DRAG

-0.67

runtime

-0.65

ERAL

-0.64

ogi

-0.64

lessness

-0.64

rys

-0.62

POSITIVE LOGITS

icable

0.85

 bothered

0.73

 Enough

0.72

spo

0.72

shy

0.69

Enough

0.69

theless

0.68

 spoon

0.67

 enough

0.67

 reunited

0.65

Activations Density 0.013%

this neuron is looking for instances where something is almost but not entirely fitting or meeting expectations

phrases indicating uncertainty or hesitation

No Comments

No Known Activations